© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 207283
    Prev
    Next
    INDEX
    Explanations

    id properties or variable declarations

    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_25_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
     системи
    0.35
     Sino
    0.35
     Лу
    0.34
     poles
    0.33
    πτωση
    0.33
     درون
    0.33
    侦
    0.33
     Между
    0.32
     кое
    0.32
     \
    0.32
    POSITIVE LOGITS
    ენტის
    0.34
    ુક
    0.33
     naš
    0.33
     indiqu
    0.32
    during
    0.31
     incurable
    0.31
     kaps
    0.31
     särsk
    0.31
    remark
    0.31
     দূর
    0.31
    Activations Density 0.000%

    No Known Activations