© 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. 123154
    Prev
    Next
    INDEX
    Explanations

    patch usage

    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
    ه
    0.74
    ב
    0.72
     alcalde
    0.69
     argentino
    0.65
    هي
    0.64
    ف
    0.64
    ה
    0.64
     ancienne
    0.63
     There
    0.61
     angrily
    0.61
    POSITIVE LOGITS
    p
    0.87
    al
    0.77
    el
    0.74
    of
    0.73
    son
    0.69
    um
    0.66
    g
    0.65
    il
    0.64
    。
    0.63
    ар
    0.63
    Activations Density 0.003%

    No Known Activations