© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231192
    Prev
    Next
    INDEX
    Explanations

    snatch or snatched

    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_6_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
    ی
    0.93
    padă
    0.89
    يبه
    0.79
    م
    0.79
    ために
    0.79
    手的
    0.78
    ಿಂತ
    0.77
    椃
    0.76
    ﺒ
    0.75
    м
    0.75
    POSITIVE LOGITS
    ре
    1.13
    us
    1.07
    _
    1.06
    V
    1.06
    LE
    1.02
    For
    0.99
    il
    0.96
    :
    0.93
    ма
    0.93
    ;
    0.93
    Activations Density 0.000%

    No Known Activations