© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39215
    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_57_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
     покуп
    0.42
     вверх
    0.42
    uidor
    0.42
     compras
    0.41
     Seems
    0.38
     покупки
    0.38
    帽
    0.38
    encias
    0.37
     Purchases
    0.37
     gravit
    0.36
    POSITIVE LOGITS
     conoc
    0.44
     radiated
    0.40
    ಂತಹ
    0.39
    $>$
    0.38
     conhe
    0.38
    deposited
    0.38
    registered
    0.37
     แห
    0.37
     मस्
    0.37
    Isolated
    0.37
    Activations Density 0.000%

    No Known Activations