© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49122
    Prev
    Next
    INDEX
    Explanations

    jazz and harmony

    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_31_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
     holster
    0.38
     dail
    0.38
     пси
    0.36
    套
    0.36
     ribbons
    0.35
    蚩
    0.35
     Waffen
    0.34
    行人
    0.34
    FAO
    0.33
    FBSDKGraph
    0.33
    POSITIVE LOGITS
     Jazz
    0.73
    Jazz
    0.65
     jazz
    0.62
    jazz
    0.59
     jaz
    0.54
     Night
    0.45
     night
    0.43
     noct
    0.43
     夜
    0.42
    soir
    0.41
    Activations Density 0.021%

    No Known Activations