© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 316
    Prev
    Next
    INDEX
    Explanations

    javascript export statements

    oai_token-act-pair · gemini-2.0-flash

    export

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     oprot
    -0.73
    RenderAtEndOf
    -0.58
    export
    -0.57
    zeczytaj
    -0.56
    kháu
    -0.56
     export
    -0.55
    AutoScale
    -0.55
    Captor
    -0.53
    hloromethane
    -0.52
    <?
    -0.52
    POSITIVE LOGITS
    XSSF
    0.52
     defStyleAttr
    0.51
    undial
    0.51
    jspx
    0.50
     Sunt
    0.48
     Inspiration
    0.47
    Gön
    0.46
     pozn
    0.45
    addCriterion
    0.44
    inspira
    0.44
    Activations Density 1.160%

    No Known Activations