© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154989
    Prev
    Next
    INDEX
    Explanations

    Year or number

    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_50_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
     San
    1.41
     san
    1.35
    San
    1.31
     삼
    1.30
     SAN
    1.25
    삼
    1.21
    san
    1.14
    三
    1.11
     سان
    1.09
     Сан
    1.02
    POSITIVE LOGITS
    <unused78>
    0.39
     पंड
    0.38
     grat
    0.38
    Modulo
    0.38
    <unused26>
    0.36
    ilib
    0.36
    檔
    0.36
    MOR
    0.36
     korzyst
    0.34
     gratification
    0.34
    Activations Density 0.002%

    No Known Activations