© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49664
    Prev
    Next
    INDEX
    Explanations

    HTML attributes: `id`, `onclick`, `disabled`, `style`, `alt`

    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_31_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
     ಬೀ
    0.43
    ielt
    0.39
    䂝
    0.37
     скры
    0.37
     수를
    0.35
    及び
    0.35
     Amn
    0.35
     invisibility
    0.35
    လျ
    0.35
    xor
    0.34
    POSITIVE LOGITS
    між
    0.39
    etze
    0.39
     landscaped
    0.38
    틋
    0.37
     applying
    0.37
    ziehungen
    0.36
    zeichnung
    0.36
     hiked
    0.36
     interposed
    0.36
     меж
    0.36
    Activations Density 0.003%

    No Known Activations