© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163187
    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_31_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
     \\
    0.38
     intersection
    0.36
    overleftarrow
    0.36
     omnip
    0.35
    eneva
    0.35
     \$
    0.34
     January
    0.34
     intersects
    0.33
    sol
    0.33
    nda
    0.33
    POSITIVE LOGITS
    ilikom
    0.41
    Alien
    0.39
     Atra
    0.39
     Attraction
    0.38
    hevik
    0.38
    Serious
    0.38
    ابع
    0.37
    加坡
    0.37
    簹
    0.37
     Facility
    0.37
    Activations Density 0.000%

    No Known Activations