© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172092
    Prev
    Next
    INDEX
    Explanations

    styled components Box div

    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_20_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
    कृपया
    0.39
    ⓵
    0.39
    andte
    0.39
    溶解
    0.39
     देखिए
    0.38
    these
    0.38
    oxet
    0.38
     BOTH
    0.38
    綢
    0.38
     utilice
    0.37
    POSITIVE LOGITS
     handicapped
    0.48
     harass
    0.47
    인을
    0.46
     территория
    0.46
     TCL
    0.45
     exalted
    0.44
    ໆ
    0.42
    ген
    0.42
    ều
    0.41
     అన్న
    0.41
    Activations Density 0.000%

    No Known Activations