© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77160
    Prev
    Next
    INDEX
    Explanations

    and

    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_53_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
     그런데
    0.40
     ...
    0.36
     ero
    0.34
     근데
    0.33
    னைய
    0.33
    specific
    0.33
    versed
    0.33
     [...]
    0.33
     আসার
    0.32
     (...)
    0.32
    POSITIVE LOGITS
    ək
    0.42
     إ
    0.41
    getFocusAreas
    0.41
     Donec
    0.40
     أ
    0.39
    캿
    0.38
    聶
    0.37
     iguais
    0.37
    झन
    0.37
    ectar
    0.37
    Activations Density 0.000%

    No Known Activations