© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209473
    Prev
    Next
    INDEX
    Explanations

    rust / rusting

    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_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
     longer
    0.48
     intensiv
    0.45
     hossz
    0.45
     dług
    0.45
     leggera
    0.45
     w
    0.44
    idium
    0.44
     anim
    0.44
     experts
    0.44
     delay
    0.43
    POSITIVE LOGITS
    mbito
    0.53
    Disk
    0.46
     الخير
    0.46
    Frames
    0.44
    OJ
    0.44
    Fmat
    0.43
     ഓര്‍
    0.43
    Outputs
    0.43
    achelor
    0.42
    .].
    0.42
    Activations Density 0.000%

    No Known Activations