© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56851
    Prev
    Next
    INDEX
    Explanations

    still, yet, sure, surely, now

    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_11_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
    ی
    0.74
     Ман
    0.68
     funzione
    0.58
    ي
    0.58
    ﺭ
    0.57
    ों
    0.57
    )،
    0.55
     McGuire
    0.55
    нер
    0.55
     quantità
    0.54
    POSITIVE LOGITS
    at
    0.90
    น
    0.64
    o
    0.63
    as
    0.61
    ட்ட
    0.59
    ع
    0.55
    ना
    0.54
    n
    0.54
    ak
    0.54
    ن
    0.53
    Activations Density 0.000%

    No Known Activations