© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77581
    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_53_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
     săn
    0.44
    蛭
    0.41
    Nah
    0.40
    ënten
    0.40
    ディング
    0.39
    ствовать
    0.38
     butt
    0.38
     sert
    0.38
    velopp
    0.38
    гән
    0.38
    POSITIVE LOGITS
    an
    0.45
    AN
    0.43
     슬
    0.42
    出し
    0.41
    anne
    0.40
     Aust
    0.38
     Auger
    0.38
    ForeignKey
    0.38
     outlets
    0.37
     francis
    0.37
    Activations Density 0.000%

    No Known Activations