© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7329
    Prev
    Next
    INDEX
    Explanations

    code snippets including HTML, Javascript, and C

    oai_token-act-pair · gemini-2.0-flash

    Code and tags

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Bets
    -0.74
     Hats
    -0.73
     Buds
    -0.71
     Pits
    -0.71
     Bars
    -0.71
    chips
    -0.69
     itſelf
    -0.69
     Guns
    -0.69
     Chips
    -0.68
     ſtate
    -0.68
    POSITIVE LOGITS
     Christiansen
    0.64
     Communications
    0.60
    SerializedSize
    0.57
    STRUCTIONS
    0.56
     Structures
    0.56
    Communications
    0.54
     COMMUNICATIONS
    0.53
     Relationships
    0.53
     Pharmaceuticals
    0.52
    теристики
    0.50
    Activations Density 7.827%

    No Known Activations