© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174807
    Prev
    Next
    INDEX
    Explanations

    juice

    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_20_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
    ú
    0.31
     Olímp
    0.30
     Sebastián
    0.30
    ó
    0.30
    ío
    0.29
     espíritu
    0.29
     María
    0.28
    naio
    0.28
    éticos
    0.28
     अमृता
    0.28
    POSITIVE LOGITS
    WATER
    0.31
    PackageManager
    0.30
    гез
    0.30
    PEM
    0.29
     تړ
    0.29
     ջ
    0.29
     WATER
    0.28
    어야
    0.28
    鱻
    0.28
    bted
    0.28
    Activations Density 0.001%

    No Known Activations