© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129216
    Prev
    Next
    INDEX
    Explanations

    More [descriptor]

    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_6_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
    u
    1.38
    I
    1.38
    L
    1.34
    A
    1.30
    z
    1.26
    C
    1.25
    ,
    1.23
    B
    1.23
    و
    1.21
    -
    1.20
    POSITIVE LOGITS
    ли
    1.16
    ре
    1.06
    ライン
    0.98
    場合
    0.94
    ονται
    0.93
    ్రియ
    0.90
    רי
    0.90
     ヒ
    0.89
     デ
    0.89
    д
    0.88
    Activations Density 0.010%

    No Known Activations