© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134696
    Prev
    Next
    INDEX
    Explanations

    home

    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_37_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
    чему
    0.40
    ‹
    0.38
     (+
    0.36
     एक्सपे
    0.36
     ஒத்து
    0.36
     (@
    0.36
     EMU
    0.36
     Ata
    0.36
     supposedly
    0.36
    eco
    0.35
    POSITIVE LOGITS
    enschappen
    0.38
     mérite
    0.38
    创业
    0.37
    henderit
    0.37
     کھیلوں
    0.37
    获
    0.35
     الوق
    0.35
    айл
    0.35
    chließlich
    0.35
    权的
    0.35
    Activations Density 0.000%

    No Known Activations