© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54633
    Prev
    Next
    INDEX
    Explanations

    connection fails

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    ولت
    0.24
     constancy
    0.22
     frug
    0.21
     fornis
    0.21
     semblance
    0.21
    кту
    0.21
     ruffle
    0.20
     subtilis
    0.20
     conserv
    0.20
    藕
    0.20
    POSITIVE LOGITS
    yd
    0.22
     스테
    0.21
     Language
    0.21
    agées
    0.21
     THOR
    0.20
    细
    0.20
    cular
    0.20
    四
    0.19
    Powers
    0.19
     Languages
    0.19
    Activations Density 0.058%

    No Known Activations