© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81094
    Prev
    Next
    INDEX
    Explanations

    extreme or negative

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    ⌬
    0.42
     noticeable
    0.38
     શક
    0.38
     некоторое
    0.38
     ग
    0.37
     Mar
    0.37
     aton
    0.37
     melon
    0.37
     mar
    0.37
     ’
    0.37
    POSITIVE LOGITS
    liches
    0.46
    ͅ
    0.41
    лично
    0.40
    ̣i
    0.40
     ఎమ్
    0.38
     UTA
    0.38
    y
    0.38
    ্তি
    0.38
    Haus
    0.38
    keiten
    0.38
    Activations Density 0.000%

    No Known Activations