© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129648
    Prev
    Next
    INDEX
    Explanations

    в этом

    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_1_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
     for
    2.13
    '
    1.64
    ’
    1.56
    i
    1.49
     in
    1.44
     في
    1.38
     by
    1.33
     σε
    1.30
    is
    1.21
     لأ
    1.20
    POSITIVE LOGITS
    ն
    1.22
    他的
    1.11
    었다
    1.07
    ک
    1.05
    ב
    0.98
    みを
    0.97
    ます
    0.96
    しばらく
    0.96
    し
    0.96
    маш
    0.95
    Activations Density 0.000%

    No Known Activations