© 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. 78451
    Prev
    Next
    INDEX
    Explanations

    code function parameters

    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
    ZE
    0.33
     Rise
    0.33
     різ
    0.33
     ±
    0.32
     शब्दों
    0.31
     sticker
    0.31
     Drain
    0.31
    ismet
    0.31
    ябрь
    0.31
    篩
    0.31
    POSITIVE LOGITS
    Jakarta
    0.38
     Jakarta
    0.37
     Jacket
    0.33
    JAK
    0.33
     collaborating
    0.32
    Numero
    0.32
    Anno
    0.31
    㿟
    0.31
     JAK
    0.31
     шабло
    0.31
    Activations Density 0.000%

    No Known Activations