© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103137
    Prev
    Next
    INDEX
    Explanations

    R L O S E D M A M E

    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_1_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
    ב
    1.30
    Y
    1.20
     at
    1.20
     an
    1.18
     are
    1.16
    {
    1.13
    కు
    1.11
    И
    1.08
     is
    1.06
    I
    1.06
    POSITIVE LOGITS
    )};
    1.02
    م
    0.97
    ல்
    0.96
    yl
    0.94
    ;
    0.92
    tede
    0.89
    āju
    0.88
    ів
    0.86
    ’।
    0.85
    ère
    0.83
    Activations Density 0.007%

    No Known Activations