© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135970
    Prev
    Next
    INDEX
    Explanations

    discs or distinct digits

    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
     streptomycin
    0.41
    🥄
    0.39
     باشه
    0.38
     হইয়াছে
    0.38
    หร่
    0.38
    夥
    0.37
     hazelnuts
    0.37
    вак
    0.37
    ুব্ধ
    0.36
    िणी
    0.35
    POSITIVE LOGITS
     Fortaleza
    0.41
     Ángeles
    0.38
     Disk
    0.38
     discs
    0.38
     Toute
    0.37
     flicks
    0.37
    europa
    0.36
    ulu
    0.36
    Ĉ
    0.36
     Disc
    0.36
    Activations Density 0.001%

    No Known Activations