© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135056
    Prev
    Next
    INDEX
    Explanations

    Madrid, penalty, semicolon

    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_37_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
    除去
    0.41
    λλη
    0.38
     suitable
    0.38
    ExpireTime
    0.37
     userId
    0.37
     꺼
    0.37
     shallow
    0.35
     Woj
    0.35
     Gallows
    0.35
    ----+
    0.34
    POSITIVE LOGITS
     لن
    0.39
    Rol
    0.38
    Chia
    0.38
     фер
    0.38
     flor
    0.37
    ネル
    0.37
    viet
    0.36
     Molina
    0.36
     అంశ
    0.36
     çi
    0.36
    Activations Density 0.000%

    No Known Activations