© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 47109
    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_13_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
    in
    0.50
    Tac
    0.46
    Suzuki
    0.45
     Schwier
    0.44
    S
    0.44
    padă
    0.44
    𝐆
    0.43
     passionately
    0.42
    tac
    0.42
    u
    0.41
    POSITIVE LOGITS
    ड्रन
    0.50
    ieving
    0.48
    ர்களை
    0.48
    ಕ್ಕೆ
    0.47
    anzen
    0.47
    ierte
    0.47
    φος
    0.47
     NAA
    0.46
    URF
    0.46
    royd
    0.46
    Activations Density 0.000%

    No Known Activations