© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 137671
    Prev
    Next
    INDEX
    Explanations

    major negative events

    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_37_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
     Problems
    0.43
    ह
    0.42
     problems
    0.42
    经历
    0.40
     проблемы
    0.40
    ต์
    0.39
     erreurs
    0.39
    經歷
    0.39
     tasar
    0.39
     пробле
    0.38
    POSITIVE LOGITS
    maps
    0.38
    awie
    0.36
    麃
    0.36
    eki
    0.35
    ന്യൂ
    0.35
    miktar
    0.35
    }";
    0.35
     browserSync
    0.35
    䔬
    0.35
    ugio
    0.34
    Activations Density 0.003%

    No Known Activations