© 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. 82053
    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
     k
    0.46
    kich
    0.41
    NoError
    0.39
    Tomato
    0.38
     Brooke
    0.37
    attach
    0.37
    က
    0.37
    Bitmap
    0.36
    Printf
    0.35
    Bread
    0.35
    POSITIVE LOGITS
     Phrases
    0.40
     verbs
    0.40
     ॥
    0.39
    లిన
    0.39
     Г
    0.38
     Фа
    0.38
     Exactly
    0.38
     রক্তের
    0.38
     αξ
    0.37
    ﻟ
    0.37
    Activations Density 0.000%

    No Known Activations