© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9611
    Prev
    Next
    INDEX
    Explanations

    the words "has", "had", "have", "having", "is", "am", "are", "having", "with", "to", "not", "made", "a", combined with personal pronouns & related possessive pronouns and adjectives.

    oai_token-act-pair · gemini-2.0-flash

    quantifiers or expressions of quantity

    np_token-act-pair-logits · gpt-4o-mini

    Quantifiers and articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.78
    parsedMessage
    -0.76
    
    -0.72
    providedIn
    -0.71
    __()
    -0.69
    WebElementEntity
    -0.68
     <>",
    -0.68
     estekak
    -0.66
    __":
    -0.66
    NameValuePair
    -0.63
    POSITIVE LOGITS
     lots
    0.82
     a
    0.82
     this
    0.77
     plenty
    0.73
     that
    0.68
     an
    0.66
     many
    0.65
     these
    0.64
     the
    0.64
     those
    0.62
    Activations Density 2.290%

    No Known Activations