© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33091
    Prev
    Next
    INDEX
    Explanations

    array is sorted

    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_40_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
     Extension
    0.44
     ಸ್ನೇ
    0.40
    Extension
    0.40
    extension
    0.39
     व्र
    0.39
     Solicitor
    0.39
    <0x16>
    0.38
    Uuid
    0.38
     ethics
    0.37
    🄴
    0.37
    POSITIVE LOGITS
    を持
    0.39
     contiennent
    0.39
    rought
    0.38
    enders
    0.38
     Utilizamos
    0.38
    bm
    0.37
    エリー
    0.37
    proud
    0.36
    wes
    0.36
     consiste
    0.35
    Activations Density 0.000%

    No Known Activations