© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 149766
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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_60_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
    ↵
    0.88
     (
    0.48
     (‘
    0.46
    (-
    0.43
     ("
    0.42
     ('
    0.39
    ’)
    0.39
    ilità
    0.39
                          
    0.38
    arı
    0.38
    POSITIVE LOGITS
    Msg
    0.53
    ↵↵
    0.49
    А
    0.47
    W
    0.45
     ~,
    0.44
     Msg
    0.43
    S
    0.43
    Bill
    0.42
    Ag
    0.42
    孟
    0.42
    Activations Density 0.001%

    No Known Activations