© 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. 149879
    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
    ی
    0.56
     analysts
    0.51
    ASP
    0.48
    ኹ
    0.48
     superstructure
    0.46
    GRADE
    0.46
    DAS
    0.45
     monomer
    0.45
    PSG
    0.43
     receptacle
    0.42
    POSITIVE LOGITS
    ítő
    0.54
     ග
    0.52
     Californ
    0.52
     Cups
    0.52
     Thro
    0.52
     Kik
    0.49
    avio
    0.49
     віднов
    0.48
    玷
    0.48
     கோவில்
    0.48
    Activations Density 0.000%

    No Known Activations