© 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. 124877
    Prev
    Next
    INDEX
    Explanations

    chrome options or trees

    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
    IL
    0.69
    یم
    0.69
    ED
    0.68
    یت
    0.66
    یس
    0.65
    ごはん
    0.64
    보
    0.63
    LOG
    0.61
    )。
    0.61
    ó
    0.61
    POSITIVE LOGITS
    0
    0.78
     август
    0.64
    l
    0.58
    st
    0.57
    stion
    0.56
    al
    0.54
     uncanny
    0.54
     একটা
    0.53
    I
    0.53
    мна
    0.52
    Activations Density 0.000%

    No Known Activations