© 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. 214658
    Prev
    Next
    INDEX
    Explanations

    egg, shell, cigarette, cells

    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
     eradic
    0.59
    ϭ
    0.57
     ions
    0.56
     Maze
    0.55
     semn
    0.54
     italics
    0.54
     égales
    0.52
    ঙ্কের
    0.51
     Maf
    0.50
     Atth
    0.50
    POSITIVE LOGITS
    sung
    0.48
    lisher
    0.48
     տար
    0.47
    荤
    0.47
    method
    0.47
     telegraph
    0.46
    願意
    0.46
    BE
    0.46
    stdout
    0.46
    窑
    0.46
    Activations Density 0.039%

    No Known Activations