© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 208398
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    its
    0.49
    ski
    0.47
    that
    0.46
    ting
    0.46
    skull
    0.45
    ।
    0.43
    GetString
    0.43
     skis
    0.42
     of
    0.41
     groupBox
    0.41
    POSITIVE LOGITS
    ﺓ
    0.55
    Tn
    0.52
     defectos
    0.52
     வழங்க
    0.50
    رهای
    0.50
    πηρε
    0.50
     پلا
    0.50
     perone
    0.50
     Пер
    0.49
     zweite
    0.49
    Activations Density 0.000%

    No Known Activations