© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84616
    Prev
    Next
    INDEX
    Explanations

    journal entry detailing

    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_0_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
    ě
    1.45
    ۔
    1.37
    1.33
    .
    1.33
    are
    1.30
    知道
    1.27
    ні
    1.23
    '
    1.20
    。
    1.20
    ern
    1.13
    POSITIVE LOGITS
    ט
    1.89
    ين
    1.79
    ח
    1.63
    기
    1.51
    ला
    1.38
    К
    1.38
    드
    1.38
    та
    1.33
    스
    1.31
    на
    1.30
    Activations Density 0.001%

    No Known Activations