© 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. 204031
    Prev
    Next
    INDEX
    Explanations

    Excel sheet names

    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
     consola
    0.36
    ‿
    0.36
     Hardware
    0.35
     вали
    0.35
     dificultad
    0.35
     کاری
    0.34
     Wiring
    0.34
    𒂵
    0.34
    ेच्छा
    0.33
    badbreak
    0.33
    POSITIVE LOGITS
    ГО
    0.42
    ध्या
    0.40
     überw
    0.38
     dziś
    0.38
     ماس
    0.38
    พ
    0.38
    itimes
    0.38
     பூம
    0.37
    omass
    0.37
     totally
    0.37
    Activations Density 0.000%

    No Known Activations