© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202014
    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_6_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
     \
    1.34
     to
    1.20
    ire
    1.16
    ue
    1.11
    ot
    1.06
    nie
    1.06
    4
    1.02
    og
    1.01
    to
    1.00
     by
    0.99
    POSITIVE LOGITS
    ’
    1.30
    ת
    1.12
    א
    1.04
    تك
    0.98
    त
    0.94
    ותו
    0.91
    ता
    0.91
    та
    0.90
    ির
    0.90
    ո
    0.90
    Activations Density 0.000%

    No Known Activations