© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142771
    Prev
    Next
    INDEX
    Explanations

    least

    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_46_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
     Expanded
    0.41
    の意味
    0.39
    يدية
    0.37
     ginseng
    0.37
    泮
    0.37
    ഭാ
    0.36
     indecent
    0.35
     Einsch
    0.35
    льника
    0.35
     의미
    0.34
    POSITIVE LOGITS
    catch
    0.42
    确认
    0.41
    天的
    0.39
     heavens
    0.39
     up
    0.38
    天
    0.37
    拥有
    0.37
     আজি
    0.36
    却
    0.36
     .”
    0.36
    Activations Density 0.001%

    No Known Activations