© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 216267
    Prev
    Next
    INDEX
    Explanations

    import statement context

    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_16_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
    šu
    0.23
    )<\
    0.23
    ostal
    0.23
    conductivity
    0.23
     internationale
    0.23
    arily
    0.22
    öhn
    0.22
    students
    0.22
     k
    0.22
     천
    0.22
    POSITIVE LOGITS
    餌
    0.23
     punctato
    0.22
     meravigli
    0.21
    ปล
    0.21
     Mercier
    0.21
    咧
    0.21
    ⠑
    0.20
    ベイ
    0.20
     Camper
    0.20
    しないで
    0.20
    Activations Density 0.007%

    No Known Activations