© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199158
    Prev
    Next
    INDEX
    Explanations

    empirical risk minimization

    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_12_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
    রামর্শ
    0.52
     टाई
    0.51
     ३
    0.49
     Alloys
    0.49
     Temperaturen
    0.49
     Thermal
    0.48
     ـ
    0.47
     இதையடுத்து
    0.47
     temperatures
    0.46
     udara
    0.46
    POSITIVE LOGITS
    czka
    0.59
    σε
    0.55
    attham
    0.52
    Eb
    0.52
    kommer
    0.52
    ch
    0.52
    uric
    0.52
    atil
    0.52
    hovah
    0.51
    </h1>
    0.51
    Activations Density 0.001%

    No Known Activations