© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202381
    Prev
    Next
    INDEX
    Explanations

    retraining programs

    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_12_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
     hígado
    0.58
    <0xAA>
    0.55
    <0xB1>
    0.52
    키
    0.51
    キ
    0.51
     ácidos
    0.50
     radically
    0.49
    '
    0.48
     Municipal
    0.47
     House
    0.46
    POSITIVE LOGITS
    Teacher
    0.57
    学历
    0.55
    teacher
    0.54
    Badge
    0.54
    macd
    0.54
    DatePicker
    0.54
    Stylesheet
    0.53
    Deferred
    0.52
     Fleurit
    0.52
    WebApi
    0.52
    Activations Density 0.001%

    No Known Activations