© 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. 126506
    Prev
    Next
    INDEX
    Explanations

    backward integration

    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
     freno
    0.39
     santa
    0.38
     فوق
    0.34
     cal
    0.34
     februari
    0.34
     alimentaires
    0.34
    雪
    0.33
     Laur
    0.33
    औ
    0.33
     Inv
    0.32
    POSITIVE LOGITS
     Vertical
    0.54
     Backward
    0.54
     vertical
    0.53
     backward
    0.52
    積分
    0.51
     integrate
    0.50
     VERT
    0.50
     vertically
    0.50
    integrate
    0.50
    Vertical
    0.49
    Activations Density 0.002%

    No Known Activations