© 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. 17816
    Prev
    Next
    INDEX
    Explanations

    Medical initials and mental

    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
    тех
    0.40
    Impress
    0.38
     ottimo
    0.37
    ATIVES
    0.36
    كال
    0.36
     Padding
    0.35
    িতেছি
    0.35
    棕
    0.35
    鹑
    0.35
    Excellent
    0.34
    POSITIVE LOGITS
    ┝
    0.38
     dissolved
    0.34
    même
    0.34
     ዋ
    0.34
    četně
    0.34
    陼
    0.34
     dissolve
    0.33
     BAC
    0.33
    ᾷ
    0.33
     ‎
    0.33
    Activations Density 0.002%

    No Known Activations