© 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. 39578
    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
    Actual
    0.41
    żeli
    0.41
     Actual
    0.40
     desired
    0.39
     đốc
    0.39
    improved
    0.38
    棫
    0.38
    actual
    0.38
     能力
    0.37
    ನ್ನೂ
    0.37
    POSITIVE LOGITS
    
    0.45
     controlling
    0.44
     capital
    0.44
    RelativeTo
    0.41
     becoming
    0.40
     lump
    0.39
    TorpedoStore
    0.39
     Controlling
    0.39
    ईआरटी
    0.38
     begin
    0.37
    Activations Density 0.000%

    No Known Activations