© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 44982
    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
    Negative Logits
     dimost
    0.48
    singer
    0.47
    <0x0D>
    0.47
    synt
    0.47
    affection
    0.47
     demonstr
    0.46
    synth
    0.46
    Synt
    0.45
    nThe
    0.45
     Theory
    0.45
    POSITIVE LOGITS
     положение
    0.48
     tractable
    0.47
    比如说
    0.47
    轵
    0.45
     savk
    0.45
    부
    0.43
     I
    0.43
    стика
    0.43
     технология
    0.42
    杰
    0.42
    Activations Density 0.000%

    No Known Activations