© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29606
    Prev
    Next
    INDEX
    Explanations

    bat

    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_10_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
    (
    0.85
    3
    0.68
    ES
    0.63
    unn
    0.58
     ينا
    0.58
    uli
    0.54
    ਆਂ
    0.54
    4
    0.54
    es
    0.53
    Phones
    0.52
    POSITIVE LOGITS
    ال
    0.72
    на
    0.69
     unethical
    0.69
    ש
    0.68
    த
    0.68
     sitios
    0.67
    bardziej
    0.66
     impacto
    0.64
     sombre
    0.64
     invern
    0.64
    Activations Density 0.000%

    No Known Activations