© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32625
    Prev
    Next
    INDEX
    Explanations

    Princeton University, Institute for Advanced Study

    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
     సందర్భ
    0.38
     nonzero
    0.38
    দো
    0.38
     ез
    0.36
     क्रिया
    0.35
    論文
    0.34
    ≺
    0.34
     Dryden
    0.34
     mcc
    0.34
    हली
    0.33
    POSITIVE LOGITS
     playtime
    0.38
    Qatar
    0.35
    $">
    0.34
     Olympi
    0.33
     autoridad
    0.33
     shavings
    0.33
     maths
    0.33
    金属
    0.33
     aritmética
    0.33
    chron
    0.32
    Activations Density 0.000%

    No Known Activations