© 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. 201917
    Prev
    Next
    INDEX
    Explanations

    fuel system components

    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
     ref
    0.45
     Filling
    0.43
     Ref
    0.40
     Filled
    0.38
     refill
    0.38
    ref
    0.38
    側
    0.37
    鑲
    0.37
     guitars
    0.37
     Calibration
    0.37
    POSITIVE LOGITS
    閲覧
    0.39
    atoren
    0.39
     negotiate
    0.39
    Ret
    0.39
    Hei
    0.38
    Lotus
    0.38
    Balanced
    0.38
    Drinking
    0.37
    Negoti
    0.37
    ESH
    0.37
    Activations Density 0.000%

    No Known Activations