© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231479
    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_6_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
    ing
    1.80
    il
    1.63
    im
    1.50
    em
    1.48
    re
    1.40
    q
    1.37
    us
    1.36
    ha
    1.36
    ur
    1.32
    le
    1.31
    POSITIVE LOGITS
    ي
    1.04
     vostri
    0.96
     jeopardize
    0.94
     tuoi
    0.93
     doh
    0.92
    ്
    0.89
     dedos
    0.88
     danni
    0.87
     mouve
    0.86
     nerveux
    0.85
    Activations Density 0.000%

    No Known Activations