© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126088
    Prev
    Next
    INDEX
    Explanations

    consumption patterns

    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
     श्रेय
    0.39
     Meh
    0.37
     corresponden
    0.37
    蜕
    0.37
    marginLeft
    0.36
    OrderFlight
    0.36
    wenden
    0.36
    摇
    0.36
    assemble
    0.35
     सेक
    0.35
    POSITIVE LOGITS
     patterns
    0.61
     pattern
    0.57
    Patterns
    0.49
     Patterns
    0.49
    パターン
    0.49
    pattern
    0.48
     Consumption
    0.48
     Pattern
    0.46
    Pattern
    0.46
     패턴
    0.44
    Activations Density 0.000%

    No Known Activations