© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63587
    Prev
    Next
    INDEX
    Explanations

    '

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    With
    0.46
    「
    0.45
     My
    0.44
    My
    0.43
    cre
    0.42
    『
    0.41
    ``
    0.40
     Мы
    0.40
     This
    0.40
    Vanilla
    0.39
    POSITIVE LOGITS
    ve
    0.66
    ’
    0.56
    VE
    0.53
    ве
    0.48
     vei
    0.47
     causa
    0.45
     gxh
    0.44
     VEGFR
    0.43
     BOARDSIZE
    0.42
     ९
    0.42
    Activations Density 0.002%

    No Known Activations