© 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. 109810
    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
    il
    0.96
    el
    0.82
    in
    0.75
    er
    0.75
    ur
    0.74
    en
    0.72
    ↵
    0.71
    K
    0.66
     can
    0.62
    at
    0.61
    POSITIVE LOGITS
    3
    1.03
    .
    0.82
    𝟯
    0.80
    ス
    0.77
    های
    0.72
    の前
    0.71
    ла
    0.70
    ді
    0.70
    t
    0.69
    ę
    0.68
    Activations Density 0.000%

    No Known Activations