© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46498
    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_10_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
     बाई
    0.54
    Facade
    0.53
    U
    0.52
     हुन्छ
    0.52
    Split
    0.48
    Shr
    0.48
    C
    0.48
     np
    0.47
    AG
    0.46
     yerden
    0.46
    POSITIVE LOGITS
     accompany
    0.48
    드의
    0.45
    କ
    0.45
     Serving
    0.44
     تھیں۔
    0.44
     aula
    0.42
    این
    0.42
     accompagner
    0.41
    </thead>
    0.40
    㫴
    0.40
    Activations Density 0.000%

    No Known Activations