© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134160
    Prev
    Next
    INDEX
    Explanations

    database migrations

    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_37_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
    തിനാൽ
    0.41
    दा
    0.41
    вершен
    0.40
    數字
    0.40
    ल्हे
    0.39
    ｙ
    0.39
    verz
    0.38
    ковое
    0.37
    ówczas
    0.37
    =?";
    0.37
    POSITIVE LOGITS
     Lle
    0.38
     llu
    0.37
     cocktail
    0.37
     Pierre
    0.35
     Cred
    0.35
     pośred
    0.35
    રૂ
    0.34
    न्ह
    0.34
     Chilean
    0.33
     llrp
    0.33
    Activations Density 0.000%

    No Known Activations