© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40429
    Prev
    Next
    INDEX
    Explanations

    product launches

    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
     szí
    0.57
    iten
    0.53
    est
    0.52
    ée
    0.50
     targets
    0.50
     paran
    0.49
     might
    0.49
     ă
    0.47
     și
    0.47
    叫
    0.47
    POSITIVE LOGITS
     ಕೊಟ್ಟ
    0.70
    DEF
    0.66
    Recommendation
    0.65
    Diagonal
    0.64
    Largest
    0.62
    Stability
    0.61
    റൽ
    0.61
    Statistical
    0.61
    Maximum
    0.60
    δου
    0.58
    Activations Density 0.000%

    No Known Activations