© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211239
    Prev
    Next
    INDEX
    Explanations

    爆炸式增，扩散式传播

    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_5_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
     It
    1.38
     Ι
    1.17
    ク
    1.12
     А
    1.07
     Име
    1.06
    )،
    1.05
     О
    1.03
    ‘
    1.02
     for
    1.01
     as
    1.01
    POSITIVE LOGITS
    は
    1.38
     to
    1.27
    at
    1.25
    dır
    1.25
    6
    1.25
    ба
    1.23
    AR
    1.13
    8
    1.09
    ę
    1.09
    га
    1.09
    Activations Density 0.000%

    No Known Activations