© 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. 205934
    Prev
    Next
    INDEX
    Explanations

    mix

    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
    률
    0.41
     انه
    0.36
    rosyn
    0.36
     CONCLUS
    0.34
     î
    0.34
    locking
    0.34
     sweats
    0.34
     TESTS
    0.33
     emitters
    0.33
    饅
    0.33
    POSITIVE LOGITS
     mix
    2.67
     Mix
    2.47
    mix
    2.38
    Mix
    2.36
     mixes
    2.05
    MIX
    1.88
     MIX
    1.83
     mixture
    1.68
    ミックス
    1.66
     मिक्स
    1.58
    Activations Density 0.002%

    No Known Activations