© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125327
    Prev
    Next
    INDEX
    Explanations

    section header

    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
     A
    0.83
    A
    0.75
     I
    0.73
    ↵↵
    0.72
     R
    0.71
     U
    0.68
     P
    0.63
     V
    0.62
     S
    0.61
    _
    0.61
    POSITIVE LOGITS
    اک
    0.77
     فونٹ
    0.70
    ری
    0.68
    یم
    0.65
    یر
    0.64
    ми
    0.63
    یی
    0.63
    اکر
    0.62
    atthena
    0.61
     আশংকা
    0.61
    Activations Density 0.001%

    No Known Activations