© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211048
    Prev
    Next
    INDEX
    Explanations

    mixins

    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_5_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
    ați
    0.61
    ер
    0.56
    <0x8C>
    0.54
    :
    0.52
    но
    0.52
    el
    0.49
     в
    0.49
    nach
    0.48
    eqn
    0.48
    ao
    0.48
    POSITIVE LOGITS
     It
    0.83
    มัน
    0.65
    </h2>
    0.65
    ک
    0.64
    the
    0.63
    </a>
    0.60
    高
    0.60
    <0x0D>
    0.59
    </u>
    0.59
    সে
    0.57
    Activations Density 0.000%

    No Known Activations