© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204954
    Prev
    Next
    INDEX
    Explanations

    user request

    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_25_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
    hydration
    0.42
    𝘀
    0.41
     पाणी
    0.39
     Tien
    0.38
     प्रया
    0.38
     মেহে
    0.38
    Kaynak
    0.38
     ল
    0.37
     Há
    0.37
    पर्या
    0.36
    POSITIVE LOGITS
     athe
    0.38
    ractive
    0.36
    oclip
    0.36
    ,$$
    0.35
    ctr
    0.34
    rivial
    0.33
     hypersurfaces
    0.33
    abled
    0.33
    itl
    0.33
    roversial
    0.32
    Activations Density 0.000%

    No Known Activations