© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25679
    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_10_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
    |।
    0.49
     gurus
    0.48
     Akt
    0.46
    כם
    0.46
     natürliche
    0.46
     كده
    0.45
    _|
    0.45
    _[
    0.45
    zne
    0.44
    鬱
    0.44
    POSITIVE LOGITS
     falsehood
    0.51
     આપી
    0.48
    picker
    0.43
     specificity
    0.43
     शकेल
    0.43
     처음
    0.43
     произведение
    0.42
    lowing
    0.42
     культура
    0.42
     основ
    0.42
    Activations Density 0.000%

    No Known Activations