© 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. 34584
    Prev
    Next
    INDEX
    Explanations

    experimental results show

    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
    and
    0.89
    Experimental
    0.74
    지와
    0.64
    정과
    0.64
    ް
    0.64
    على
    0.63
    実験
    0.63
    dır
    0.61
     эксперимента
    0.61
     and
    0.60
    POSITIVE LOGITS
    ри
    0.82
    ви
    0.73
    к
    0.73
    "
    0.71
    н
    0.71
    _
    0.68
    น
    0.63
    "}}
    0.63
    </h4>
    0.61
    <0x0D>
    0.61
    Activations Density 0.003%

    No Known Activations