© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43172
    Prev
    Next
    INDEX
    Explanations

    it is about

    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
     лес
    0.16
     Holliday
    0.15
     jTextField
    0.15
     Siddhartha
    0.14
    ᱓
    0.14
     কিন্তু
    0.14
     Jensen
    0.14
    新たな
    0.14
    પૂર્ણ
    0.14
     Rent
    0.14
    POSITIVE LOGITS
     dragState
    0.15
     구분
    0.15
     xử
    0.15
     heels
    0.14
    Sunglasses
    0.14
    neze
    0.14
    演
    0.14
     consultation
    0.14
     역할
    0.14
     multip
    0.13
    Activations Density 0.016%

    No Known Activations