© 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. 254012
    Prev
    Next
    INDEX
    Explanations

    not

    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
     Franz
    0.43
     cannot
    0.39
     wage
    0.39
    cannot
    0.38
     কাটা
    0.38
     up
    0.38
     find
    0.37
    ₡
    0.36
    起来
    0.36
     
    0.36
    POSITIVE LOGITS
    hin
    0.61
     sure
    0.57
     Sure
    0.47
    sure
    0.46
    hend
    0.46
    Sure
    0.45
     SURE
    0.43
     needing
    0.43
    her
    0.42
    h
    0.41
    Activations Density 0.005%

    No Known Activations