© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159262
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ﭼ
    0.68
    ли
    0.67
     conducir
    0.64
    ﻣ
    0.63
     crédito
    0.60
     considér
    0.60
     конферен
    0.59
    ﺧ
    0.59
     in
    0.59
    ן
    0.58
    POSITIVE LOGITS
    to
    0.65
    on
    0.61
    es
    0.56
    an
    0.56
     on
    0.56
     Palisades
    0.55
    ک
    0.53
     Konstant
    0.49
    v
    0.49
    a
    0.48
    Activations Density 0.000%

    No Known Activations