© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200017
    Prev
    Next
    INDEX
    Explanations

    promptingguide.ai

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     वत्स
    0.43
     goblin
    0.40
     Galactic
    0.39
    सरण
    0.39
     Vasa
    0.39
     Elastic
    0.38
     Elasticsearch
    0.38
    致
    0.38
    Gob
    0.38
     tehn
    0.38
    POSITIVE LOGITS
    ソッド
    0.41
    otone
    0.39
     حمد
    0.37
     catalogues
    0.36
     Conjecture
    0.36
     بیاکتنې
    0.36
    吨
    0.36
     conjecture
    0.35
    HAM
    0.34
     تناول
    0.34
    Activations Density 0.002%

    No Known Activations