© 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. 85836
    Prev
    Next
    INDEX
    Explanations

    Icarus, Ikaria, Greece

    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
    3
    0.71
    5
    0.70
    il
    0.67
    {
    0.64
    ()
    0.63
     April
    0.62
    kan
    0.62
    ANG
    0.61
    .
    0.61
    4
    0.61
    POSITIVE LOGITS
    क्स
    0.82
    اک
    0.80
     virulent
    0.77
    ᐟ
    0.74
    𝒔
    0.73
    ্সি
    0.70
    arası
    0.70
    စျေး
    0.69
    
    0.68
    añas
    0.68
    Activations Density 0.000%

    No Known Activations