© 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. 9202
    Prev
    Next
    INDEX
    Explanations

    code snippets, specifically C or Go code including return statements, curly braces, and URL paths

    oai_token-act-pair · gemini-2.0-flash

    foreign language characters or words

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

    Code

    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
    Personensuche
    -0.92
     الرياضيه
    -0.91
    IVEREF
    -0.88
     تانيه
    -0.83
    ?')
    -0.82
    ".
    -0.82
    Gambas
    -0.82
    )";
    -0.78
    ")));
    -0.77
    Cyfeiriadau
    -0.76
    POSITIVE LOGITS
    мя
    0.45
    ագրություններ
    0.43
    ług
    0.42
     personalità
    0.40
     ponad
    0.40
     personalidade
    0.40
     mengen
    0.40
     unui
    0.39
     próprios
    0.39
    CE
    0.38
    Activations Density 1.894%

    No Known Activations