© 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. 5643
    Prev
    Next
    INDEX
    Explanations

    text near legal jargon and names in legal documents

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to data or metadata

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

    legal documents

    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
    httphttps
    -0.51
    EndContext
    -0.42
     Conrad
    -0.40
     res
    -0.40
    loyds
    -0.39
    printStackTrace
    -0.39
    سوب
    -0.38
    étisme
    -0.38
    WriteAttribute
    -0.38
    río
    -0.38
    POSITIVE LOGITS
     VizieR
    0.88
    principalTable
    0.81
    GEBURTSDATUM
    0.80
     unknownFields
    0.79
    ContentAsync
    0.77
     tartalomajánló
    0.75
    MessageOf
    0.72
     فريبيس
    0.71
    참고
    0.69
    RenderAtEndOf
    0.69
    Activations Density 0.833%

    No Known Activations