© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3202
    Prev
    Next
    INDEX
    Explanations

    discussions of difficulty or inability to do something, as well as discussion of health and nutrition.

    oai_token-act-pair · gemini-2.0-flash

    foreign language tokens or names

    np_token-act-pair-logits · gpt-4o-mini

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     implementation
    -1.77
     Implementation
    -1.69
    implementation
    -1.66
     implementing
    -1.61
    Implementation
    -1.56
     implement
    -1.55
     implementations
    -1.52
    Implementing
    -1.49
    implement
    -1.49
     implemented
    -1.49
    POSITIVE LOGITS
     democracia
    0.46
    entuk
    0.46
     zvuky
    0.42
     säll
    0.42
    ריך
    0.41
    newswire
    0.41
    createNewFile
    0.41
     nacionales
    0.39
     gehö
    0.39
     skå
    0.39
    Activations Density 1.741%

    No Known Activations