© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236182
    Prev
    Next
    INDEX
    Explanations

    low sodium, reduced sugar, alcohol removed

    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_32_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
    urname
    0.39
    ើង
    0.38
     shaded
    0.37
     desag
    0.37
    rava
    0.37
    中部
    0.37
     fus
    0.36
     母
    0.36
     sconf
    0.36
     hak
    0.36
    POSITIVE LOGITS
     Reduced
    0.46
    Reduced
    0.43
     reduced
    0.39
     आर्य
    0.38
     ಹೋ
    0.36
     Holocaust
    0.35
    渾
    0.35
    点を
    0.34
     Versand
    0.34
     किं
    0.33
    Activations Density 0.001%

    No Known Activations