© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124969
    Prev
    Next
    INDEX
    Explanations

    closing parentheses

    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_37_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
     joe
    0.40
     thùng
    0.40
     Overall
    0.38
    㡱
    0.38
     .-
    0.38
    chh
    0.37
     Halke
    0.37
     автомо
    0.36
    둴
    0.36
    ائن
    0.36
    POSITIVE LOGITS
     CAP
    0.39
    Lei
    0.39
    ule
    0.38
    usi
    0.38
    aries
    0.38
    rogen
    0.38
     મા
    0.37
    Aber
    0.37
    SIE
    0.37
     phase
    0.36
    Activations Density 0.006%

    No Known Activations