© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237878
    Prev
    Next
    INDEX
    Explanations

    failure rates

    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_32_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
     numbers
    0.22
     संख्याओं
    0.20
    謚
    0.19
     थोड़ा
    0.19
     परीक्षाओं
    0.19
     Vac
    0.18
     Imports
    0.18
     Klass
    0.17
    numbers
    0.17
     Numbers
    0.17
    POSITIVE LOGITS
    anton
    0.19
    DBObject
    0.19
    opolitical
    0.18
    훤
    0.18
     hendak
    0.18
    QRect
    0.17
    Lc
    0.17
     wants
    0.17
    faction
    0.17
    லோச
    0.17
    Activations Density 0.007%

    No Known Activations