© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213606
    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_5_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
    ة
    1.77
    as
    1.70
    os
    1.65
    on
    1.55
    ing
    1.47
    з
    1.38
    is
    1.38
    с
    1.38
    an
    1.37
    ia
    1.30
    POSITIVE LOGITS
     of
    1.13
     agir
    1.08
     augmente
    1.03
    lari
    1.02
     impediments
    1.02
     extravaganza
    1.02
     absur
    0.98
     abrog
    0.98
     cranks
    0.98
     acumul
    0.97
    Activations Density 0.000%

    No Known Activations