© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3818
    Prev
    Next
    INDEX
    Explanations

    instances of the word "get" and related forms

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating a request or demand

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

    get

    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
    ScopeManager
    -1.02
     '\\;'
    -0.91
    }\]
    -0.79
     tartalomajánló
    -0.77
    ureusement
    -0.73
     whereof
    -0.73
    .")]
    -0.73
     виправивши
    -0.73
     estekak
    -0.71
     שוליים
    -0.70
    POSITIVE LOGITS
     self
    0.51
     into
    0.46
     an
    0.46
     di
    0.46
     f
    0.46
     cross
    0.46
     him
    0.44
     caught
    0.44
     off
    0.44
     mad
    0.44
    Activations Density 0.656%

    No Known Activations