© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7455
    Prev
    Next
    INDEX
    Explanations

    temperature ranges

    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_39_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ൧
    0.28
    OfString
    0.28
    uelve
    0.27
    yra
    0.26
     –,
    0.26
    াকাছি
    0.26
    群体
    0.26
     nineteen
    0.26
    손
    0.26
     নিয়ে
    0.25
    POSITIVE LOGITS
    bele
    0.31
    额外
    0.29
     Certificates
    0.28
    പം
    0.28
    env
    0.26
    pek
    0.25
     новую
    0.25
     इलेक्ट्र
    0.25
     otev
    0.25
     PRIM
    0.25
    Activations Density 0.026%

    No Known Activations