© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198393
    Prev
    Next
    INDEX
    Explanations

    drawing a, happy dance

    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_4_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
     that
    0.93
    <0x0D>
    0.92
    。
    0.88
    ２
    0.88
    </h5>
    0.86
    0.86
    that
    0.85
    ur
    0.85
     defensor
    0.84
     ज़िन्दगी
    0.83
    POSITIVE LOGITS
    the
    0.85
    <0xAC>
    0.82
    eth
    0.78
    ography
    0.78
    ene
    0.77
    asters
    0.76
    ,
    0.75
    ess
    0.74
    ש
    0.74
    ING
    0.73
    Activations Density 0.035%

    No Known Activations