© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198025
    Prev
    Next
    INDEX
    Explanations

    USCIS

    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_4_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
    a
    0.73
    ють
    0.64
    -
    0.62
     agreg
    0.56
     が
    0.55
     afirm
    0.55
     lanç
    0.54
    тся
    0.52
     écrit
    0.52
     asegur
    0.51
    POSITIVE LOGITS
    ot
    0.80
    ib
    0.68
    خ
    0.66
    iz
    0.62
    ح
    0.62
    w
    0.61
    uk
    0.61
    ad
    0.59
    ap
    0.58
    ü
    0.57
    Activations Density 0.004%

    No Known Activations