© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 90448
    Prev
    Next
    INDEX
    Explanations

    opening parentheses

    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_23_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     labeled
    0.47
    也是
    0.46
     hemolytic
    0.44
     också
    0.43
     tachycardia
    0.42
    齜
    0.42
     ebenfalls
    0.42
    labeled
    0.41
     depletion
    0.41
    大家的
    0.40
    POSITIVE LOGITS
     도전
    0.41
     jeu
    0.39
    quier
    0.38
     выборах
    0.38
    QUI
    0.37
    ♠
    0.37
     Donation
    0.36
    PrivateKey
    0.36
     बद
    0.35
    reira
    0.35
    Activations Density 0.000%

    No Known Activations