© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91700
    Prev
    Next
    INDEX
    Explanations

    испаряет, истежући, prime

    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
    1.48
    s
    1.34
    A
    1.09
    p
    1.06
    '
    1.06
    in
    1.03
    ac
    0.95
    ach
    0.90
    ς
    0.90
    the
    0.89
    POSITIVE LOGITS
    ری
    1.34
    یک
    1.01
    り
    0.89
    یس
    0.88
    ِی
    0.85
    中の
    0.84
    異なります
    0.84
    ли
    0.83
    لی
    0.83
    انی
    0.82
    Activations Density 0.000%

    No Known Activations