© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116498
    Prev
    Next
    INDEX
    Explanations

    code processing and data manipulation

    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_27_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
     caratter
    0.35
     ինչ
    0.34
     catégories
    0.33
    use
    0.33
    ඵ
    0.33
     använd
    0.33
     použív
    0.33
     bordering
    0.32
    conserv
    0.32
    drivers
    0.32
    POSITIVE LOGITS
     기도
    0.35
     직원
    0.33
     대회
    0.33
     এন্টি
    0.33
    ఒ
    0.32
     молит
    0.32
     нулю
    0.31
    罪
    0.31
     другу
    0.31
     покупки
    0.31
    Activations Density 0.006%

    No Known Activations