© 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. 214434
    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
    in
    1.80
    il
    1.56
    at
    1.47
    .
    1.34
    اية
    1.22
    ா
    1.21
    ோ
    1.20
    ි
    1.20
    k
    1.19
    า
    1.19
    POSITIVE LOGITS
     و
    1.16
     an
    1.09
     (
    1.03
     autopilot
    1.01
     kunde
    0.99
     abstracts
    0.95
     ACH
    0.94
     quarries
    0.94
     subtype
    0.92
     disparities
    0.91
    Activations Density 0.000%

    No Known Activations