© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6683
    Prev
    Next
    INDEX
    Explanations

    the word "model", sometimes near the words "wheel", "configuration", and "ratio"

    oai_token-act-pair · gemini-2.0-flash

    model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -0.80
     Pre
    -0.78
     Back
    -0.75
     model
    -0.73
     Un
    -0.72
     van
    -0.71
     It
    -0.71
     One
    -0.69
     (
    -0.67
     [
    -0.67
    POSITIVE LOGITS
    <bos>
    1.97
     Efq
    1.30
     raiſ
    1.24
     itſelf
    1.23
     myſelf
    1.23
     Monfieur
    1.23
     feroit
    1.18
     himſelf
    1.16
    InjectAttribute
    1.15
     ainfi
    1.13
    Activations Density 1.176%

    No Known Activations