© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112215
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ться
    1.01
     언
    0.96
     반
    0.95
    лта
    0.93
    د
    0.92
    ack
    0.91
     불
    0.91
     crackdown
    0.91
     geolocation
    0.91
     패
    0.89
    POSITIVE LOGITS
    ı
    1.73
    ING
    1.42
    í
    1.34
    ü
    1.26
    ী
    1.25
    ة
    1.16
    ва
    1.09
    ように
    1.02
    és
    1.01
    場合の
    1.00
    Activations Density 0.000%

    No Known Activations