© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130831
    Prev
    Next
    INDEX
    Explanations

    you're right 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_6_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
    ای
    1.00
    '
    0.92
    ק
    0.88
    ’
    0.86
    の後
    0.84
    ון
    0.82
    od
    0.81
    اس
    0.80
    وک
    0.80
    립니다
    0.76
    POSITIVE LOGITS
    l
    1.13
    s
    1.12
    t
    1.08
    k
    1.05
    a
    1.04
    ่
    1.03
    y
    1.00
    ta
    0.99
    lą
    0.95
    lø
    0.94
    Activations Density 0.002%

    No Known Activations