© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207396
    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
    ᒡ
    0.47
    кр
    0.47
     пресс
    0.43
    啮
    0.43
    責任
    0.43
    autoprefixer
    0.42
    ੁਰ
    0.41
    ステップ
    0.41
    売
    0.41
     프리
    0.40
    POSITIVE LOGITS
     ihm
    0.49
    ie
    0.48
     diesem
    0.47
     detection
    0.46
     seria
    0.46
     groupes
    0.45
    ancy
    0.45
    ienie
    0.45
     erklären
    0.45
     qui
    0.44
    Activations Density 0.000%

    No Known Activations