© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211329
    Prev
    Next
    INDEX
    Explanations

    end of list items

    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
    レ
    0.39
     redo
    0.38
     오래
    0.36
    sham
    0.36
     winger
    0.35
    ager
    0.35
     fire
    0.35
     fret
    0.35
     creer
    0.35
     soin
    0.34
    POSITIVE LOGITS
     Blocks
    0.42
     Components
    0.42
     Removes
    0.40
    ຜະລິດຕະພັນ
    0.39
    ເລັກ
    0.38
     .{
    0.38
     Sanitation
    0.38
     обстоятельства
    0.38
    ဖို့
    0.38
     Membranes
    0.38
    Activations Density 0.000%

    No Known Activations