© 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. 30900
    Prev
    Next
    INDEX
    Explanations

    provide immediate

    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
     வன
    0.35
     корреспонд
    0.32
     Trust
    0.32
    趴
    0.31
     unscrupulous
    0.31
     friendly
    0.31
     stunned
    0.30
     joe
    0.30
     ঘুষ
    0.30
     stamp
    0.30
    POSITIVE LOGITS
     Established
    0.34
     المحاضره
    0.33
    舫
    0.33
    aisesti
    0.33
     Membership
    0.32
     Generations
    0.32
     Lessons
    0.31
    analisi
    0.31
    olu
    0.31
    ->_
    0.30
    Activations Density 0.007%

    No Known Activations