© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257809
    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_22_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
     satellite
    0.45
     compression
    0.44
     dependence
    0.43
     disability
    0.43
    >,</
    0.43
    )?;
    0.43
     commens
    0.43
     glass
    0.42
     proliferative
    0.42
     modal
    0.42
    POSITIVE LOGITS
    ﻓ
    0.49
    𝖊
    0.48
    uriken
    0.48
     версии
    0.47
     этих
    0.47
    メイク
    0.47
     اتب
    0.46
    
    0.46
    コード
    0.46
     ಭ
    0.46
    Activations Density 0.000%

    No Known Activations