© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199679
    Prev
    Next
    INDEX
    Explanations

    $ followed by n or number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
    <unused1079>
    0.39
    inser
    0.38
     succesfully
    0.38
    イオン
    0.38
    𒆜
    0.38
     flawlessly
    0.37
     Marken
    0.37
    ಿಂತ
    0.37
     correctement
    0.37
    gaard
    0.36
    POSITIVE LOGITS
    Fish
    0.38
    мл
    0.38
    Field
    0.36
    善
    0.36
    sp
    0.36
    Language
    0.35
    Should
    0.35
     semantics
    0.35
    fish
    0.35
    Property
    0.34
    Activations Density 0.003%

    No Known Activations