© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130313
    Prev
    Next
    INDEX
    Explanations

    court paragraphe

    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_1_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
    ли
    1.41
    ла
    1.23
     niektórych
    0.98
    </h3>
    0.96
    ため
    0.96
    ल
    0.95
    স্বর
    0.94
     sumptuous
    0.93
     northeastern
    0.91
    他的
    0.89
    POSITIVE LOGITS
    i
    1.55
    ،
    1.54
    in
    1.38
    an
    1.36
    ه
    1.34
    e
    1.33
    a
    1.32
     was
    1.27
    k
    1.18
     on
    1.17
    Activations Density 0.001%

    No Known Activations