© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230703
    Prev
    Next
    INDEX
    Explanations

    doing what's right

    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_6_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
    em
    1.13
    et
    1.12
    un
    0.99
    os
    0.91
    ar
    0.90
    Em
    0.90
    ’
    0.89
    um
    0.88
    es
    0.83
    দের
    0.83
    POSITIVE LOGITS
     offenders
    0.79
    ۰
    0.77
    butadiene
    0.71
     чувство
    0.68
    ;
    0.67
    ربی
    0.66
     interfacing
    0.62
     ακό
    0.61
    لیس
    0.61
     %).
    0.61
    Activations Density 0.001%

    No Known Activations