© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5515
    Prev
    Next
    INDEX
    Explanations

    language used for describing the legal system, including discussions about the frequency or repetition of events, and statements of fact

    oai_token-act-pair · gemini-2.0-flash

    occasion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    脚注の使い方
    -0.91
    ViewFeatures
    -0.80
     Shakspeare
    -0.74
     Houſe
    -0.73
     houſe
    -0.73
    CloseOperation
    -0.73
     Shaksp
    -0.73
     Jefus
    -0.71
     invokingState
    -0.70
    PullParser
    -0.70
    POSITIVE LOGITS
     occasion
    1.81
     occasions
    1.80
    occasion
    1.51
     Occasion
    1.37
     ocasión
    1.31
     occas
    1.23
     instances
    1.20
    occas
    1.20
    Occasion
    1.16
     ocas
    1.14
    Activations Density 0.990%

    No Known Activations