© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88804
    Prev
    Next
    INDEX
    Explanations

    truth be told or truth about

    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_3_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
    s
    1.02
    人
    0.95
    多
    0.79
    ها
    0.78
    il
    0.77
    க
    0.74
    ng
    0.73
    ों
    0.73
    ين
    0.71
    일
    0.70
    POSITIVE LOGITS
     fillColorSpace
    0.64
    ian
    0.60
    стите
    0.59
    ところで
    0.59
     kerusakan
    0.56
    esch
    0.55
     içeren
    0.55
    SP
    0.55
    ATIV
    0.54
    ojen
    0.54
    Activations Density 0.000%

    No Known Activations