© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34499
    Prev
    Next
    INDEX
    Explanations

    oobabooga

    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_3_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
    ك
    0.83
    ع
    0.81
     has
    0.76
    <0x0D>
    0.76
     will
    0.75
     is
    0.70
     are
    0.68
    ↵
    0.67
    ক
    0.67
    ى
    0.67
    POSITIVE LOGITS
    poem
    0.70
    ।"
    0.67
     уровне
    0.64
    methylation
    0.64
    ጠት
    0.64
    called
    0.63
    drawString
    0.63
    glacial
    0.62
    ರ್
    0.61
    butoxy
    0.61
    Activations Density 0.000%

    No Known Activations