© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204080
    Prev
    Next
    INDEX
    Explanations

    primarily, largely

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    innaker
    0.41
    atsu
    0.37
    々の
    0.35
    ]-[
    0.35
    imbo
    0.35
    ክር
    0.35
    ächst
    0.34
    linger
    0.34
     facilement
    0.34
    ₂
    0.34
    POSITIVE LOGITS
     limited
    0.74
    limited
    0.69
    Limited
    0.68
     Limited
    0.61
     limitada
    0.60
     limitado
    0.60
    LIMITED
    0.57
     सीमित
    0.57
     ограничен
    0.57
     LIMITED
    0.56
    Activations Density 0.009%

    No Known Activations