© 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. 109085
    Prev
    Next
    INDEX
    Explanations

    gargle or gargamel

    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
    t
    1.85
    و
    1.73
    the
    1.46
    j
    1.46
    ன்
    1.27
    ہ
    1.24
    İ
    1.24
    z
    1.16
    à
    1.16
    Z
    1.16
    POSITIVE LOGITS
     at
    1.10
    ?
    1.02
    1
    0.91
     acetylation
    0.88
     extraneous
    0.87
     entidades
    0.86
     asegurar
    0.86
     molyb
    0.85
     arrhyth
    0.84
     webbrowser
    0.83
    Activations Density 0.001%

    No Known Activations