© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 119429
    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_27_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
     sûr
    0.41
     posso
    0.38
     malonyl
    0.38
    哏
    0.38
     sockfd
    0.37
     суммы
    0.37
    గి
    0.37
     samtid
    0.37
    Ꮤ
    0.36
    FDMA
    0.36
    POSITIVE LOGITS
     H
    0.46
    xs
    0.44
    rec
    0.43
     h
    0.43
     Character
    0.41
    cha
    0.40
     Identity
    0.40
    s
    0.40
     Rec
    0.40
    Rec
    0.40
    Activations Density 0.000%

    No Known Activations