© 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. 146215
    Prev
    Next
    INDEX
    Explanations

    Ole

    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
    UAL
    0.45
    sız
    0.41
    h
    0.38
    ECK
    0.38
    IRS
    0.37
    ينات
    0.37
    TIMES
    0.36
    WAY
    0.36
    Heinrich
    0.36
    muse
    0.35
    POSITIVE LOGITS
    kt
    0.48
    טית
    0.44
    th
    0.44
    ologisk
    0.42
    c
    0.42
    kk
    0.41
    ks
    0.40
    ológico
    0.40
    ng
    0.39
     Pedersen
    0.39
    Activations Density 0.000%

    No Known Activations