© 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. 25116
    Prev
    Next
    INDEX
    Explanations

    news websites and tech resources

    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
    '$\
    0.22
    +\
    0.22
    등급
    0.20
     behaviours
    0.19
    خ
    0.19
    rowning
    0.18
    "},
    0.18
    +
    0.18
    ップ
    0.18
    বৃন্দ
    0.18
    POSITIVE LOGITS
    s
    0.29
    ség
    0.23
    selt
    0.22
    sı
    0.22
    ка
    0.21
     он
    0.21
    cation
    0.20
     అత
    0.19
    in
    0.19
    sion
    0.19
    Activations Density 0.045%

    No Known Activations