© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59632
    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_2_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
    ↵
    1.02
    3
    0.96
    thirty
    0.93
     ++
    0.88
    luğu
    0.88
     a
    0.86
    of
    0.86
    code
    0.86
    law
    0.83
    treatment
    0.82
    POSITIVE LOGITS
    k
    1.43
    Т
    1.26
    सी
    1.22
    К
    1.20
    kowe
    1.10
    ক
    1.09
    kker
    1.07
    kowej
    1.07
    م
    1.06
    й
    1.06
    Activations Density 0.000%

    No Known Activations