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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11469
    Prev
    Next
    INDEX
    Explanations

    transitions between prepositions, articles and quantity

    oai_token-act-pair · gemini-2.0-flash

    quantifiers related to amounts or levels

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

    quantity

    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
    Hentet
    -0.75
     ExecuteAsync
    -0.65
    AutoScaleMode
    -0.61
    cèse
    -0.61
     дописавши
    -0.61
     kaarangay
    -0.59
    +#+#
    -0.59
    contentLoaded
    -0.58
     BnF
    -0.57
    JspWriter
    -0.56
    POSITIVE LOGITS
     varying
    1.02
     greater
    0.88
     significant
    0.77
    varying
    0.71
     variable
    0.70
     considerable
    0.68
     differing
    0.67
    greater
    0.67
     sufficient
    0.66
     reasonable
    0.64
    Activations Density 2.286%

    No Known Activations