© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84226
    Prev
    Next
    INDEX
    Explanations

    constraints, numbers, exponents

    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_23_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
     Ấn
    0.46
    ုန်
    0.46
     Проци
    0.44
     ㅛ
    0.43
     Oiseau
    0.43
    辇
    0.43
    🍠
    0.42
     sắt
    0.42
     চৈতন্ত
    0.42
     브랜드
    0.42
    POSITIVE LOGITS
     visually
    0.41
     RE
    0.40
    able
    0.40
    val
    0.40
    ability
    0.39
    ABLE
    0.39
     contributing
    0.38
     reproducible
    0.38
    info
    0.38
    0
    0.38
    Activations Density 0.000%

    No Known Activations