© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 12403
    Prev
    Next
    INDEX
    Explanations

    angle brackets, quotes, colons, and other characters used in code and web pages

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash

    punctuation Method used: 1 — because MAX_ACTIVATING_TOKENS are punctuation/symbols — punctuation

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    […]
    -0.81
     Efq
    -0.78
    .³
    -0.78
     ...'
    -0.76
     itſelf
    -0.76
     doubtnut
    -0.75
    ')(
    -0.74
    )");
    
    -0.73
     ―――――
    -0.72
    }\]
    -0.72
    POSITIVE LOGITS
    <bos>
    1.30
    '
    0.86
    /*
    0.80
    //
    0.73
    ’
    0.72
    Autoritní
    0.69
     of
    0.69
    /**
    0.63
     nahilalakip
    0.61
     estimés
    0.60
    Activations Density 8.114%

    No Known Activations