© 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. 42366
    Prev
    Next
    INDEX
    Explanations

    talkative / word

    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
    1
    1.09
    the
    0.97
     the
    0.93
    _
    0.75
     présente
    0.75
    e
    0.71
     be
    0.70
     plak
    0.70
     hohe
    0.65
    高手
    0.65
    POSITIVE LOGITS
    لي
    0.71
    ть
    0.69
    ूल
    0.68
    ни
    0.66
    在
    0.64
    ım
    0.62
    و
    0.62
    Л
    0.62
    point
    0.61
    ELL
    0.61
    Activations Density 0.044%

    No Known Activations