© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61356
    Prev
    Next
    INDEX
    Explanations

    in today's digital world

    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_11_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
    t
    0.65
    _
    0.62
    to
    0.56
     plaques
    0.56
     polysaccharides
    0.55
     variétés
    0.54
    സർ
    0.54
    carbonyl
    0.53
     installiert
    0.53
    da
    0.52
    POSITIVE LOGITS
    ну
    0.54
     क्वेश्चन
    0.50
     بالټ
    0.49
     excused
    0.46
    ﻒ
    0.46
    нут
    0.46
    বছ
    0.46
     ARTICLE
    0.45
     कमर
    0.45
    雰
    0.45
    Activations Density 0.001%

    No Known Activations