© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126436
    Prev
    Next
    INDEX
    Explanations

    quiche

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ко
    1.00
    ه
    0.85
    ی
    0.75
    a
    0.75
    защи
    0.68
    ের
    0.65
     *}
    0.64
    ի
    0.64
    자가
    0.63
    াৰ
    0.62
    POSITIVE LOGITS
    D
    0.85
    ou
    0.78
    Tan
    0.76
    il
    0.73
    ح
    0.73
    berly
    0.72
    ם
    0.70
    ،
    0.70
    K
    0.69
    Say
    0.68
    Activations Density 0.000%

    No Known Activations