© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12544
    Prev
    Next
    INDEX
    Explanations

    varied, but its highest activations appear for URLs, file paths, and words associated with project management

    oai_token-act-pair · gemini-2.0-flash

    documentation and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    amaño
    -0.68
     StatelessWidget
    -0.56
    ⚽
    -0.54
     Souhaitez
    -0.53
    KEYCODE
    -0.53
    celona
    -0.53
     截
    -0.52
     SECT
    -0.52
     guitarra
    -0.50
    VIAF
    -0.50
    POSITIVE LOGITS
    ViewFeatures
    0.69
    aarrggbb
    0.64
     betweenstory
    0.61
     ""],
    0.59
    __))
    0.57
    triangleq
    0.55
     ProtoMessage
    0.55
    ngilizce
    0.54
    ftagPool
    0.53
    PYX
    0.52
    Activations Density 0.194%

    No Known Activations