© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 88650
    Prev
    Next
    INDEX
    Explanations

    boba, bobdylan, babadook, bobber

    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
     I
    0.86
     a
    0.79
    a
    0.75
    il
    0.72
     an
    0.70
     It
    0.68
    an
    0.66
    C
    0.66
     A
    0.66
    for
    0.62
    POSITIVE LOGITS
     tagReport
    0.71
     потери
    0.62
     pequenas
    0.60
    -------*/
    0.59
    <unused35>
    0.59
     команды
    0.59
    лед
    0.58
     sesize
    0.58
     inférieure
    0.58
     இருப்பினும்
    0.57
    Activations Density 0.000%

    No Known Activations