© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 145785
    Prev
    Next
    INDEX
    Explanations

    keyboard, coffee, climate, sermon, forward

    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_18_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
    丁
    0.49
    टर
    0.48
    Din
    0.48
    今後の
    0.47
    चिक
    0.45
     будущем
    0.45
    म
    0.45
    트
    0.44
    千万
    0.44
    C
    0.43
    POSITIVE LOGITS
     osm
    0.57
     lc
    0.48
     bridal
    0.48
    łąd
    0.47
    änge
    0.47
     seo
    0.47
     anne
    0.47
     perils
    0.46
     errors
    0.46
    ängen
    0.46
    Activations Density 0.000%

    No Known Activations