© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37102
    Prev
    Next
    INDEX
    Explanations

    say "bl"

    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
     se
    0.57
     се
    0.57
     so
    0.45
    เพียง
    0.41
    ста
    0.39
    just
    0.39
    so
    0.38
    啱
    0.38
     sta
    0.38
    っているので
    0.37
    POSITIVE LOGITS
     bl
    0.50
     tes
    0.45
    Bl
    0.43
     Bl
    0.42
     bli
    0.41
     Blaze
    0.40
     pais
    0.39
    bl
    0.39
     бли
    0.39
     بل
    0.39
    Activations Density 0.000%

    No Known Activations