© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 79418
    Prev
    Next
    INDEX
    Explanations

    primary issue revolves around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_29_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
     LaTeX
    0.39
    cock
    0.38
     uses
    0.37
     likes
    0.37
    بحث
    0.36
     представи
    0.35
    序
    0.35
    urel
    0.34
    oki
    0.34
     stret
    0.34
    POSITIVE LOGITS
     вси
    0.43
    
    0.41
     niente
    0.40
     wszystko
    0.39
    isição
    0.38
     tudo
    0.37
    Nothing
    0.36
    Hitpoint
    0.36
     inciso
    0.36
    이지만
    0.36
    Activations Density 0.018%

    No Known Activations