© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17776
    Prev
    Next
    INDEX
    Explanations

    Azure naming conventions

    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_40_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
    <b>
    0.51
     **
    0.48
    ［
    0.43
    mathbf
    0.42
     (**
    0.41
    ()[
    0.41
     \[
    0.41
     హీ
    0.40
    <strong>
    0.38
    .[/
    0.38
    POSITIVE LOGITS
     Alexand
    0.38
    bibitem
    0.37
    asted
    0.37
    跄
    0.37
     Ains
    0.36
     Ware
    0.36
     instr
    0.35
    ufact
    0.35
    userData
    0.35
    ειτουργ
    0.34
    Activations Density 0.028%

    No Known Activations