© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 147896
    Prev
    Next
    INDEX
    Explanations

    closing punctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     
    0.42
     ['$
    0.42
     Asia
    0.41
     {}",
    0.40
     V
    0.40
     Offset
    0.39
     {})
    0.38
     Mrs
    0.38
     Head
    0.38
    
    0.38
    POSITIVE LOGITS
    （
    0.50
    ﻢ
    0.38
    ystyrene
    0.37
    ,/*
    0.37
     perceptible
    0.37
    EVA
    0.37
    (\
    0.37
    /}{
    0.36
    /
    0.36
    ອບ
    0.36
    Activations Density 0.000%

    No Known Activations