© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37549
    Prev
    Next
    INDEX
    Explanations

    abilities: Ableton Live

    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
    ב
    0.87
    с
    0.77
    נ
    0.73
    ט
    0.73
    ن
    0.71
    ನ
    0.66
    בש
    0.65
    ও
    0.64
    у
    0.64
    し
    0.63
    POSITIVE LOGITS
    \
    0.78
    '
    0.71
     fluctuations
    0.65
     divulg
    0.64
     incentiv
    0.64
    ックス
    0.62
     fonts
    0.62
     internalized
    0.62
    ກະ
    0.62
     extrapol
    0.61
    Activations Density 0.001%

    No Known Activations