© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249964
    Prev
    Next
    INDEX
    Explanations

    way/path

    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_56_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
     c
    1.16
     ص
    0.78
    c
    0.54
    esty
    0.48
    דר
    0.47
    الص
    0.43
     con
    0.43
     că
    0.41
     C
    0.41
     cad
    0.41
    POSITIVE LOGITS
     путем
    1.41
     пут
    1.16
     шля
    1.16
    ทาง
    1.14
     ทาง
    1.03
    路
    0.97
     Weg
    0.84
    ทางการ
    0.84
     avenue
    0.83
     дорого
    0.82
    Activations Density 0.000%

    No Known Activations