© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158349
    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
    
    1.11
     acheté
    1.05
    ו
    1.05
     postoji
    1.03
    Cantidad
    1.01
    Otros
    0.99
    Czas
    0.99
    Parrocchia
    0.98
     أكثر
    0.97
     يع
    0.97
    POSITIVE LOGITS
    1.91
    ä
    1.43
    :
    1.29
    ।
    1.27
    ig
    1.20
    us
    1.19
    of
    1.17
    ;
    1.16
    。
    1.12
    ing
    1.10
    Activations Density 0.000%

    No Known Activations