© 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. 201842
    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
    '
    1.05
    at
    1.00
    ur
    0.96
    ٹ
    0.90
    ти
    0.88
    atoti
    0.86
    ка
    0.86
    ชา
    0.85
    ’
    0.83
    al
    0.82
    POSITIVE LOGITS
    q
    1.17
     c
    1.05
    س
    1.01
    л
    1.00
     \
    0.99
     There
    0.98
     ."
    0.98
     nieuw
    0.95
    á
    0.95
    people
    0.91
    Activations Density 0.000%

    No Known Activations