© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9678
    Prev
    Next
    INDEX
    Explanations

    proper nouns indicating jurisdictions like cities, counties, and states.

    oai_token-act-pair · gemini-2.0-flash

    county

    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
    Comté
    -0.44
     scand
    -0.43
    entukan
    -0.42
     Appointments
    -0.41
     Frieden
    -0.41
    zepam
    -0.40
    toja
    -0.40
    keyDown
    -0.40
     fij
    -0.40
    glo
    -0.40
    POSITIVE LOGITS
    ScopeManager
    0.81
    IntoConstraints
    0.80
     صوتيه
    0.73
    featureID
    0.72
     ExecuteAsync
    0.70
     propOrder
    0.66
     GenerationType
    0.64
    IVEREF
    0.64
     gynhyrchwyd
    0.62
    MIDDLEWARE
    0.62
    Activations Density 0.792%

    No Known Activations