© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29882
    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
     rubles
    0.52
     effecting
    0.48
     ಇದೆ
    0.47
     granul
    0.45
     debunk
    0.45
     Fermat
    0.45
    檎
    0.45
     cryptography
    0.45
     counting
    0.45
     alternation
    0.44
    POSITIVE LOGITS
    พ
    0.52
    প
    0.48
    П
    0.48
    זה
    0.47
    يك
    0.47
    êm
    0.46
    绘
    0.46
    ים
    0.46
    مل
    0.46
    jeron
    0.46
    Activations Density 0.000%

    No Known Activations