© 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. 80361
    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
     син
    0.39
    yssey
    0.38
    $-$,
    0.38
     Odyssey
    0.37
     Kyr
    0.36
    orkel
    0.36
     tý
    0.36
     Whites
    0.35
    신의
    0.35
    sch
    0.35
    POSITIVE LOGITS
    ってきた
    0.38
     backing
    0.37
     Followers
    0.37
    tabla
    0.36
    ረጋ
    0.36
    鰱
    0.36
     postage
    0.36
     empec
    0.36
     pampered
    0.36
     ক্ষমতার
    0.35
    Activations Density 0.000%

    No Known Activations