© 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. 38488
    Prev
    Next
    INDEX
    Explanations

    for further

    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
    س
    1.09
    ش
    0.88
    ?
    0.82
    لي
    0.79
    ض
    0.78
    리
    0.75
    ב
    0.75
    ع
    0.74
    ات
    0.70
    is
    0.69
    POSITIVE LOGITS
    ாதி
    0.61
    ase
    0.59
     physicist
    0.57
    aval
    0.57
    𝑨
    0.57
    il
    0.57
    tex
    0.57
     rheumatoid
    0.57
     discontinuous
    0.56
    lsulfanyl
    0.56
    Activations Density 0.008%

    No Known Activations