© 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. 61253
    Prev
    Next
    INDEX
    Explanations

    skittish, skitter

    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
     graag
    0.57
     হয়েছে
    0.53
     jeopardy
    0.50
     गम
    0.50
    𝙧
    0.50
    jší
    0.50
    edom
    0.49
     Jamaica
    0.49
    іга
    0.49
    λά
    0.49
    POSITIVE LOGITS
     در
    0.73
    in
    0.69
    Vous
    0.68
    ار
    0.66
    s
    0.66
    T
    0.64
    在
    0.64
    Мы
    0.64
    ی
    0.64
    Ме
    0.63
    Activations Density 0.000%

    No Known Activations