© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12971
    Prev
    Next
    INDEX
    Explanations

    commas specifically when near the word "as"

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    之
    -0.43
     cioccolato
    -0.43
     chêne
    -0.42
    꽃
    -0.42
     napi
    -0.42
     Schulze
    -0.42
     embarazo
    -0.41
    onia
    -0.41
    дана
    -0.41
    dotenv
    -0.41
    POSITIVE LOGITS
    principalTable
    0.79
    DockStyle
    0.76
    LEncoder
    0.71
    зулта
    0.69
     estekak
    0.67
    Referències
    0.66
    EDEFAULT
    0.65
     Italijanski
    0.65
    bootstrapcdn
    0.63
    ScopeManager
    0.61
    Activations Density 0.491%

    No Known Activations