© 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. 126277
    Prev
    Next
    INDEX
    Explanations

    aivazovsky, awazaw, Aivazovsky

    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
    s
    0.69
    string
    0.68
    ad
    0.67
    ()=>{
    0.66
    version
    0.64
    ll
    0.63
    is
    0.62
    r
    0.60
    au
    0.60
    un
    0.57
    POSITIVE LOGITS
     allons
    0.77
     arbres
    0.76
     explique
    0.74
     recomb
    0.73
     filets
    0.73
    મી
    0.71
     catégorie
    0.71
     objets
    0.71
     échantillons
    0.71
     excite
    0.70
    Activations Density 0.001%

    No Known Activations