© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 118412
    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
    ocatore
    0.41
    大于
    0.40
     ол
    0.40
     Lugar
    0.40
    otherArchive
    0.39
    𝘞
    0.39
     جاتی
    0.38
     Klo
    0.38
    涳
    0.37
     Hut
    0.37
    POSITIVE LOGITS
    tipo
    0.42
     apasion
    0.42
    強力
    0.42
     prende
    0.41
    ain
    0.41
    type
    0.40
    hma
    0.39
     interprets
    0.38
     Tunisie
    0.38
    as
    0.38
    Activations Density 0.000%

    No Known Activations