© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54160
    Prev
    Next
    INDEX
    Explanations

    Okay, great!

    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
    Not in Any Lists

    No Comments

    Negative Logits
     vows
    0.38
     着
    0.36
    ចំនួន
    0.36
    ំពោះ
    0.36
    --’
    0.35
     வரலாற்று
    0.35
    chairs
    0.35
     bese
    0.34
     ವಿಧಾನಸ
    0.34
    ijl
    0.34
    POSITIVE LOGITS
     AD
    0.36
    obit
    0.32
     Svet
    0.30
     ricon
    0.30
     海
    0.30
     میچ
    0.30
     steward
    0.29
    とお
    0.29
     Gunn
    0.29
     মির
    0.29
    Activations Density 0.010%

    No Known Activations