© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153252
    Prev
    Next
    INDEX
    Explanations

    __init__.py in python

    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_23_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
     gate
    0.42
    гов
    0.41
     channeled
    0.40
     escort
    0.39
    सौ
    0.39
    ग
    0.39
     Classics
    0.39
    ரமாக
    0.39
     Critics
    0.38
     untested
    0.38
    POSITIVE LOGITS
     indiquer
    0.39
     termo
    0.38
     किसका
    0.37
    皤
    0.36
     কিনা
    0.36
    軽量
    0.36
     abbreviation
    0.35
     puisqu
    0.35
    ക്കൊ
    0.35
    写真は
    0.35
    Activations Density 0.002%

    No Known Activations