© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44860
    Prev
    Next
    INDEX
    Explanations

    width property

    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_22_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
     tasso
    0.42
     vías
    0.39
     ousted
    0.38
     mz
    0.38
     rétro
    0.38
    āja
    0.37
    ǂ
    0.37
     incumbent
    0.37
    _'.$
    0.37
     reen
    0.37
    POSITIVE LOGITS
     ठ
    0.40
     Còn
    0.40
     కార్య
    0.40
     생각
    0.39
    事情
    0.39
     정보
    0.39
    可能
    0.38
     समय
    0.38
     видели
    0.38
     भविष्य
    0.37
    Activations Density 0.000%

    No Known Activations