© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39933
    Prev
    Next
    INDEX
    Explanations

    say "<"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    Gracias
    0.45
    Hopefully
    0.42
     icin
    0.42
    Would
    0.41
    ucose
    0.41
    萎
    0.39
     ഇരു
    0.38
    फो
    0.38
    Grazie
    0.38
    놈
    0.37
    POSITIVE LOGITS
     interdiscipl
    0.41
     >
    0.40
     whirlpool
    0.39
     dop
    0.38
     steep
    0.38
    çay
    0.38
     בי
    0.37
     וב
    0.37
     pax
    0.36
    .¹
    0.36
    Activations Density 0.002%

    No Known Activations