© 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. 34913
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    in
    0.76
    य
    0.72
    స్
    0.70
    ہ
    0.70
    ੇ
    0.68
    عت
    0.66
    en
    0.65
    د
    0.65
    ح
    0.64
    ्स
    0.63
    POSITIVE LOGITS
    r
    0.74
    lighting
    0.66
    prove
    0.66
    daily
    0.65
     طریق
    0.65
    ﻌ
    0.63
    defining
    0.63
     Corinthians
    0.61
    land
    0.60
     കഥ
    0.60
    Activations Density 0.000%

    No Known Activations