© 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. 201023
    Prev
    Next
    INDEX
    Explanations

    python.org/3

    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
    yaf
    0.44
    뷰
    0.43
     wager
    0.40
    ToDo
    0.39
     издания
    0.38
    ians
    0.38
     scan
    0.38
     scant
    0.37
     skriv
    0.37
     zoom
    0.37
    POSITIVE LOGITS
     propriétés
    0.41
     Italien
    0.40
    チェ
    0.39
    牞
    0.36
    <unused52>
    0.36
     propriété
    0.35
    事は
    0.35
    propri
    0.34
     [§
    0.34
    意大利
    0.34
    Activations Density 0.000%

    No Known Activations