© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76178
    Prev
    Next
    INDEX
    Explanations

    called upon

    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_31_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
     propriétaire
    0.39
     صاحب
    0.38
     respecto
    0.36
    irons
    0.36
     WARREN
    0.36
    揸
    0.35
    workout
    0.35
     NONINFRINGEMENT
    0.35
    Instruction
    0.34
     vitth
    0.34
    POSITIVE LOGITS
    を選択
    0.38
    hatian
    0.38
    रक्षा
    0.37
    ંડ
    0.36
     Entscheidung
    0.35
     hàm
    0.35
    ikke
    0.34
    ̃
    0.33
    เปล
    0.32
     ইতিহাস
    0.31
    Activations Density 0.000%

    No Known Activations