© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161186
    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
    '
    2.16
    ва
    1.05
    <
    0.96
    ↵
    0.96
    )
    0.95
    ೇ
    0.88
    $
    0.87
    ’
    0.87
    י
    0.87
     seduced
    0.86
    POSITIVE LOGITS
    al
    1.57
    am
    1.57
    0
    1.50
    y
    1.45
    in
    1.41
    um
    1.36
    s
    1.34
    on
    1.27
    u
    1.20
    a
    1.17
    Activations Density 0.000%

    No Known Activations