© 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. 206949
    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
    सल
    0.47
     refuted
    0.44
    षे
    0.43
     उठाया
    0.42
    祢
    0.42
     मज
    0.41
    明らか
    0.41
    କ୍
    0.41
    ᱾
    0.40
     controversies
    0.39
    POSITIVE LOGITS
     всегда
    0.50
     zawsze
    0.46
     Decomposition
    0.46
    owie
    0.44
    awatan
    0.43
     Offset
    0.42
    iejs
    0.42
     Compression
    0.41
     wiele
    0.41
     aussi
    0.40
    Activations Density 0.000%

    No Known Activations