© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8818
    Prev
    Next
    INDEX
    Explanations

    const

    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_13_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
     aner
    0.54
     d
    0.53
     a
    0.51
     o
    0.51
     ɔ
    0.50
    </
    0.50
     ε
    0.50
    atten
    0.48
    omme
    0.48
    amination
    0.47
    POSITIVE LOGITS
     лучшие
    0.59
    خبر
    0.54
    aarrggbb
    0.52
    াভাব
    0.51
    不多
    0.51
     мире
    0.51
    行为
    0.50
    세계
    0.50
    ロ
    0.50
    薫
    0.50
    Activations Density 0.000%

    No Known Activations