© 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. 127624
    Prev
    Next
    INDEX
    Explanations

    Al Sweigart, Webb, Shepard, Saud

    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
    ാ
    0.80
    า
    0.76
    ا
    0.75
    a
    0.71
    organisms
    0.69
    ް
    0.69
    emes
    0.68
    OCKED
    0.67
    populations
    0.66
    el
    0.65
    POSITIVE LOGITS
     которым
    0.73
    ના
    0.67
    ан
    0.67
     в
    0.65
     in
    0.65
     در
    0.64
    roquois
    0.64
    ز
    0.62
    и
    0.61
     disheart
    0.60
    Activations Density 0.000%

    No Known Activations