© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24837
    Prev
    Next
    INDEX
    Explanations

    used or given

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    [])
    0.50
     họ
    0.46
    )”
    0.44
    他们
    0.44
    他們
    0.44
    []);
    0.44
    พวกเขา
    0.43
     آن‌ها
    0.42
    $)
    0.42
     ليها
    0.42
    POSITIVE LOGITS
     used
    0.69
     given
    0.64
     Given
    0.56
     Used
    0.55
     second
    0.53
    Used
    0.52
    used
    0.52
    Given
    0.51
    given
    0.50
     digunakan
    0.50
    Activations Density 0.003%

    No Known Activations