© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1665
    Prev
    Next
    INDEX
    Explanations

    grid template repeat(4, 1fr)

    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_40_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
    ونية
    0.38
    鞠
    0.35
    helf
    0.32
    Food
    0.31
    Iterable
    0.31
    obo
    0.31
    емых
    0.31
    ymes
    0.31
    рни
    0.30
    슝
    0.30
    POSITIVE LOGITS
    加速度
    0.39
     -$
    0.38
     Group
    0.35
     dz
    0.34
     ziua
    0.33
    dz
    0.33
    budget
    0.32
     Dz
    0.32
     বাজেট
    0.32
     جوړونکي
    0.32
    Activations Density 0.000%

    No Known Activations