© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14346
    Prev
    Next
    INDEX
    Explanations

    \The most direct pattern I can identify is the presence of code-like structures and initialization

    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_15_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
     се
    0.36
     débit
    0.35
     wel
    0.34
     ва
    0.34
    金
    0.33
    あた
    0.31
    ان
    0.31
     vă
    0.31
     }^{-
    0.31
     רא
    0.31
    POSITIVE LOGITS
    tmp
    0.36
    🇽
    0.34
    taining
    0.34
     eds
    0.34
     täglich
    0.34
    <unused988>
    0.34
    ponses
    0.33
     atraves
    0.33
     attravers
    0.33
    龌
    0.33
    Activations Density 0.013%

    No Known Activations