© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217702
    Prev
    Next
    INDEX
    Explanations

    groups of people and their teams

    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_31_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
    玝
    0.43
    breakpoints
    0.39
    ലൈ
    0.38
    btnLogout
    0.37
    clude
    0.36
    㓩
    0.36
     ছেলেরা
    0.35
    的一次
    0.35
    εια
    0.34
    所で
    0.34
    POSITIVE LOGITS
    anzit
    0.42
     funct
    0.42
     किसने
    0.41
     administer
    0.39
    churn
    0.38
     nineties
    0.38
    誰
    0.38
     italiani
    0.37
     varies
    0.37
     কমে
    0.37
    Activations Density 0.001%

    No Known Activations