© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58653
    Prev
    Next
    INDEX
    Explanations

    over, capture, attack, take

    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_11_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
    ли
    0.63
    я
    0.55
     سیک
    0.52
    less
    0.50
     Einen
    0.50
    akit
    0.50
     İlk
    0.49
     Trotz
    0.48
     P
    0.48
    яти
    0.48
    POSITIVE LOGITS
     bowels
    0.52
    籲
    0.50
    IBLE
    0.49
    Rusty
    0.49
     coisa
    0.48
    Α
    0.48
    Sandy
    0.47
    ወዳ
    0.47
    았습니다
    0.46
    ndown
    0.46
    Activations Density 0.042%

    No Known Activations