© 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. 167409
    Prev
    Next
    INDEX
    Explanations

    function declarations

    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
     cataracts
    0.37
     inquis
    0.35
     catar
    0.35
     liturgy
    0.33
    🌬
    0.33
     cataract
    0.31
     cerrada
    0.31
     inversiones
    0.30
     tears
    0.30
     basement
    0.30
    POSITIVE LOGITS
     Successful
    0.32
    reif
    0.31
    innaker
    0.31
    ふ
    0.30
    reci
    0.29
     Decl
    0.29
    use
    0.29
    ொரு
    0.29
     Studies
    0.28
    啦
    0.28
    Activations Density 0.002%

    No Known Activations