© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14352
    Prev
    Next
    INDEX
    Explanations

    os.path checks

    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
     dp
    0.43
     Wikidata
    0.35
    ಿದ್ದ
    0.33
     Lom
    0.32
     ECD
    0.32
     Mares
    0.32
     (__
    0.32
     DP
    0.31
    Rx
    0.31
    ançon
    0.31
    POSITIVE LOGITS
     os
    1.63
     Os
    1.25
     ос
    1.20
    Os
    1.13
     OS
    1.09
     Path
    1.08
    os
    1.05
    Path
    1.00
     Osman
    0.98
    OS
    0.91
    Activations Density 0.018%

    No Known Activations