© 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. 33680
    Prev
    Next
    INDEX
    Explanations

    aphasia, athenahealth, atan2

    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
    (
    0.85
    ens
    0.83
    т
    0.79
    та
    0.75
    的三
    0.74
    ри
    0.73
    的能力
    0.73
    uje
    0.73
    trees
    0.71
    ációs
    0.69
    POSITIVE LOGITS
     as
    1.08
    פ
    0.83
     TO
    0.83
     większość
    0.82
     of
    0.80
     Film
    0.77
     {
    0.77
     OF
    0.76
    ICAL
    0.75
     '
    0.74
    Activations Density 0.006%

    No Known Activations