© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208654
    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_20_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
    斯科
    0.53
    OCO
    0.50
     石
    0.42
    対流
    0.41
    Swe
    0.40
    克
    0.40
    rng
    0.40
     λε
    0.40
    ICH
    0.39
    中に
    0.39
    POSITIVE LOGITS
     astray
    0.52
    лардан
    0.51
     concludes
    0.51
     požad
    0.51
     loudest
    0.48
     belast
    0.48
    кета
    0.47
     }^{
    0.47
    कार्ट
    0.46
     Astrid
    0.46
    Activations Density 0.000%

    No Known Activations