© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197568
    Prev
    Next
    INDEX
    Explanations

    KYC / Know Your Customer

    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_4_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
    in
    1.30
    en
    1.30
    an
    1.29
    ar
    1.27
    c
    1.27
    er
    1.17
    is
    1.02
    int
    1.02
    are
    1.02
    or
    0.99
    POSITIVE LOGITS
    И
    1.26
    ૦
    1.18
    Е
    1.15
    AY
    1.11
    А
    1.09
    ルの
    1.07
     وک
    1.05
     وی
    1.03
    َی
    1.03
    י
    1.02
    Activations Density 0.001%

    No Known Activations