© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61318
    Prev
    Next
    INDEX
    Explanations

    Far

    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
    o
    0.48
    nier
    0.47
    ുള്ള
    0.42
    ني
    0.40
    ENCED
    0.39
    ン
    0.39
    ENN
    0.39
    nym
    0.38
    nsics
    0.38
    нням
    0.38
    POSITIVE LOGITS
     Հ
    0.40
    if
    0.39
     Years
    0.38
     Where
    0.38
     дели
    0.37
     With
    0.36
     réunis
    0.36
    ultra
    0.36
    obin
    0.36
     That
    0.35
    Activations Density 0.000%

    No Known Activations