© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 57647
    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_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ।
    1.43
    。
    1.15
    with
    1.10
    0
    1.05
    ۔
    1.04
    phine
    1.03
    ،
    1.03
    ars
    1.02
    _
    1.01
     adjectives
    0.96
    POSITIVE LOGITS
    د
    1.08
    ২
    1.05
    ني
    1.04
    นี้
    1.04
    り
    1.04
    ছে
    1.01
    できる
    1.01
    ก็
    0.99
    ला
    0.98
     reflet
    0.97
    Activations Density 0.000%

    No Known Activations