© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50863
    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
    पु
    0.43
     puc
    0.40
    უკ
    0.39
     parfaite
    0.37
     prefect
    0.36
     Puis
    0.35
     Cái
    0.35
    呜
    0.34
     Pu
    0.33
     <=>
    0.33
    POSITIVE LOGITS
     treści
    0.45
    miss
    0.40
    ieden
    0.39
    Kyr
    0.39
    <0xD1>
    0.38
     sürü
    0.38
    Trab
    0.37
     dispose
    0.37
    ímav
    0.37
    Meetings
    0.37
    Activations Density 0.000%

    No Known Activations