© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6392
    Prev
    Next
    INDEX
    Explanations

    legal procedure sentence structure

    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_39_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
     expedient
    0.41
    ༄
    0.38
    ανα
    0.38
     underpinning
    0.37
     prive
    0.37
     herein
    0.37
     शुक्ला
    0.36
    ξε
    0.35
     Hương
    0.35
    顛
    0.35
    POSITIVE LOGITS
     Odd
    0.43
     Fad
    0.40
     fad
    0.39
     Rod
    0.39
     Chart
    0.38
     Church
    0.38
     Fac
    0.38
     chart
    0.38
     binge
    0.37
     रिमाइंडर
    0.37
    Activations Density 0.047%

    No Known Activations