© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 88303
    Prev
    Next
    INDEX
    Explanations

    Di

    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_60_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
    all
    0.57
    gl
    0.55
    groups
    0.55
    y
    0.54
    man
    0.53
    or
    0.51
    as
    0.51
    n
    0.51
    map
    0.50
    group
    0.50
    POSITIVE LOGITS
     Ç
    0.54
     ç
    0.52
     ş
    0.50
    Ç
    0.50
    ץ
    0.50
     زمانی
    0.47
     By
    0.44
    ç
    0.42
    şağı
    0.42
     Eğ
    0.42
    Activations Density 0.000%

    No Known Activations