© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195090
    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_50_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
    
    0.39
     jumping
    0.38
    jumping
    0.38
    しかった
    0.36
     sö
    0.35
    Intercept
    0.35
    ம்பிய
    0.35
    Pressure
    0.35
    pose
    0.35
    スペ
    0.34
    POSITIVE LOGITS
     b
    0.44
     unes
    0.42
     c
    0.41
    บ
    0.40
     Bard
    0.40
    ba
    0.39
     مکتی
    0.39
     სამ
    0.39
    Bar
    0.38
    jima
    0.38
    Activations Density 0.000%

    No Known Activations