© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87478
    Prev
    Next
    INDEX
    Explanations

    proof, bees, branches

    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
    with
    0.81
     with
    0.68
    dengan
    0.66
    na
    0.64
    지
    0.63
    dependent
    0.60
    s
    0.59
    ast
    0.57
    min
    0.57
    sworth
    0.56
    POSITIVE LOGITS
    ف
    0.76
     diverso
    0.75
    дой
    0.74
    ру
    0.73
     avrà
    0.72
     destac
    0.70
    ك
    0.70
     diffère
    0.69
    লা
    0.69
     défendre
    0.67
    Activations Density 0.000%

    No Known Activations