© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92550
    Prev
    Next
    INDEX
    Explanations

    get involved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_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
    ي
    0.80
    annte
    0.68
    ال
    0.67
    ’),
    0.59
    agés
    0.57
    rás
    0.57
     الري
    0.56
    ಿಕೆ
    0.56
     الك
    0.56
     ನೋಡ
    0.55
    POSITIVE LOGITS
    روی
    0.58
    ולם
    0.58
    8
    0.58
    々の
    0.57
    7
    0.57
    5
    0.55
     dolar
    0.54
    ولی
    0.54
    S
    0.53
    Habitat
    0.52
    Activations Density 0.000%

    No Known Activations