© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3711
    Prev
    Next
    INDEX
    Explanations

    heavier elements and lightest elements

    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_40_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
    Carbon
    0.55
     Carbon
    0.55
    carbon
    0.54
     carbon
    0.53
     carbons
    0.49
     CARBON
    0.48
     hydrocarbon
    0.48
    碳
    0.47
     carbonic
    0.46
     ocean
    0.46
    POSITIVE LOGITS
    تاء
    0.42
     nuclei
    0.42
     severance
    0.39
     Geom
    0.37
     ভারী
    0.36
     geodesic
    0.36
     капи
    0.36
    govor
    0.35
     Lyle
    0.35
     ملازمت
    0.35
    Activations Density 0.074%

    No Known Activations