© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15079
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate emphasis or absoluteness.

    oai_token-act-pair · gemini-2.0-flash

    absolute

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     absolute
    -1.06
     ABSOL
    -1.03
    absolute
    -1.03
    Absolute
    -0.96
    ABSOL
    -0.95
     Absolute
    -0.93
     absol
    -0.85
     absoluta
    -0.82
     абсолю
    -0.77
    absolutely
    -0.77
    POSITIVE LOGITS
    aarrggbb
    0.82
    Rüyada
    0.78
    ⓧ
    0.75
     CURIAM
    0.66
    ">//
    0.64
    }],
    0.63
    पया
    0.63
    "]);
    0.62
    "});
    0.61
    chartInstance
    0.60
    Activations Density 23.599%

    No Known Activations