© 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. 203883
    Prev
    Next
    INDEX
    Explanations

    distances

    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
    Not in Any Lists

    No Comments

    Negative Logits
     short
    2.70
    short
    2.36
     Short
    2.27
    短
    2.23
    Short
    2.22
     корот
    2.20
     SHORT
    2.17
     kısa
    2.08
    SHORT
    1.96
     крат
    1.91
    POSITIVE LOGITS
    oustache
    0.37
    zne
    0.35
    adillo
    0.33
    ###
    0.33
    }-(
    0.33
    rawy
    0.33
    ……………………
    0.32
    зульта
    0.32
    jih
    0.32
    ūs
    0.32
    Activations Density 0.002%

    No Known Activations