© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211122
    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
    >
    1.48
    \
    1.39
    জ
    1.30
    த
    1.27
    น
    1.27
    ব
    1.25
    ט
    1.24
    ু
    1.16
    ش
    1.15
    та
    1.13
    POSITIVE LOGITS
    ively
    1.06
    ently
    1.05
    put
    1.04
    ano
    1.04
    lymph
    1.02
    odd
    0.99
    ede
    0.98
    cretion
    0.98
    ments
    0.95
    that
    0.95
    Activations Density 0.000%

    No Known Activations