© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89212
    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_23_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
    seys
    0.43
    igur
    0.41
    ాలను
    0.39
     coins
    0.39
    lact
    0.39
     zalo
    0.38
    сову
    0.38
    틀
    0.38
    倾
    0.37
     tilting
    0.37
    POSITIVE LOGITS
     Mire
    0.52
     شبکه
    0.41
     বৃহস্পতিবার
    0.40
    recent
    0.38
     Thursday
    0.38
     रिव्यू
    0.38
    twitter
    0.38
    ൾ
    0.38
     Tuesday
    0.38
     влади
    0.37
    Activations Density 0.000%

    No Known Activations