© 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. 11701
    Prev
    Next
    INDEX
    Explanations

    code-related tokens such as file paths, functions, and tags

    oai_token-act-pair · gemini-2.0-flash

    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
    <bos>
    -0.77
    SharedCtor
    -0.66
    Демографія
    -0.56
     stepwise
    -0.54
     Whigs
    -0.54
     médié
    -0.53
     tää
    -0.51
     rhestr
    -0.51
     oír
    -0.50
     étoient
    -0.49
    POSITIVE LOGITS
    icago
    0.56
    angliski
    0.53
     صوتيه
    0.52
    исленность
    0.52
     uintptr
    0.52
    balleur
    0.51
    alha
    0.50
    oughby
    0.50
    ibatis
    0.49
     Gries
    0.49
    Activations Density 6.403%

    No Known Activations