© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20372
    Prev
    Next
    INDEX
    Explanations

    say "-al" ending

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    볼
    0.36
     볼
    0.34
     بول
    0.33
     бол
    0.32
    シン
    0.32
     Geträn
    0.32
    堑
    0.32
    мір
    0.31
    勐
    0.31
     உட்க
    0.31
    POSITIVE LOGITS
    难度
    0.37
     JES
    0.35
     tribal
    0.34
     Apica
    0.34
     práce
    0.33
     Edu
    0.33
    Ꮮ
    0.32
    ুদ্র
    0.32
    JKL
    0.32
    ᕝ
    0.32
    Activations Density 0.005%

    No Known Activations