© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248832
    Prev
    Next
    INDEX
    Explanations

    m

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     sell
    0.37
     cate
    0.34
    摽
    0.34
    Ꮀ
    0.34
     motionProxy
    0.33
    ografía
    0.33
     Suy
    0.33
    ិច្
    0.33
    çalves
    0.32
     ["[
    0.32
    POSITIVE LOGITS
     m
    2.50
     м
    2.13
     م
    1.95
     म
    1.70
     ম
    1.55
    <0xA0>
    1.48
     ம
    1.41
    ม
    1.41
    m
    1.25
     M
    1.16
    Activations Density 0.004%

    No Known Activations