© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213575
    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_5_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
    ig
    1.24
    ج
    1.20
    h
    1.20
    $
    1.18
            
    1.17
    é
    1.12
    ade
    1.11
    ess
    1.10
    س
    1.06
    ע
    1.02
    POSITIVE LOGITS
    t
    1.22
    that
    1.18
    s
    1.09
    ний
    1.05
    ナ
    1.05
    ла
    1.02
    ной
    0.97
    3
    0.97
    ﺎ
    0.90
    d
    0.88
    Activations Density 0.000%

    No Known Activations