© 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. 35732
    Prev
    Next
    INDEX
    Explanations

    nel parco, nonlinear optimization, NLTK

    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
    parties
    0.39
    ávez
    0.38
    轉
    0.38
    feel
    0.37
    médiaire
    0.37
    оз
    0.36
    ön
    0.36
     লা
    0.36
    èvement
    0.36
    頃
    0.36
    POSITIVE LOGITS
     Verify
    0.38
     Wild
    0.38
    숙
    0.37
     verify
    0.37
     conclude
    0.37
     validate
    0.36
     Symbol
    0.36
    rid
    0.35
     ended
    0.35
     penalty
    0.35
    Activations Density 0.008%

    No Known Activations