© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137146
    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_46_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
    kitty
    0.45
     schm
    0.37
     vorbei
    0.37
    総合
    0.37
    urrences
    0.37
     dunno
    0.37
    揾
    0.36
    recurring
    0.36
    ुकी
    0.36
    טת
    0.35
    POSITIVE LOGITS
     Т
    0.44
     Quill
    0.42
     phosphatase
    0.40
     Cout
    0.38
     Inter
    0.38
     ত
    0.37
     Qu
    0.37
     Input
    0.37
     QU
    0.37
     DSF
    0.37
    Activations Density 0.000%

    No Known Activations