© 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. 228104
    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
    s
    1.50
    ll
    1.16
    ?
    1.10
    ri
    0.98
    )
    0.96
    ;
    0.95
    rr
    0.89
    re
    0.89
    lo
    0.87
    ants
    0.84
    POSITIVE LOGITS
    েন
    0.94
    cích
    0.85
    ivät
    0.84
    ین
    0.81
     distância
    0.78
    SearchCV
    0.78
     سي
    0.77
    يف
    0.76
    KIN
    0.75
     കട
    0.75
    Activations Density 0.000%

    No Known Activations