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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3771
    Prev
    Next
    INDEX
    Explanations

    legal or business documents discussing rules, regulations, obligations, and disclaimers.

    oai_token-act-pair · gemini-2.0-flash

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     ſtate
    -0.68
     chofe
    -0.59
     greateſt
    -0.59
     uſed
    -0.59
     themſelves
    -0.58
     miſ
    -0.58
     houſe
    -0.57
     purpoſe
    -0.56
     quæ
    -0.56
     uſe
    -0.54
    POSITIVE LOGITS
    BufferException
    0.55
    setattr
    0.52
    ScopeManager
    0.52
    ArgsConstructor
    0.51
     виправивши
    0.51
    NLS
    0.48
    ThroughAttribute
    0.47
    MigrationBuilder
    0.46
    CO
    0.46
    Sub
    0.46
    Activations Density 1.435%

    No Known Activations