© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133654
    Prev
    Next
    INDEX
    Explanations

    dog

    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_50_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
     g
    0.65
     G
    0.64
     گ
    0.62
     ग
    0.60
     গ
    0.58
     gac
    0.57
     gant
    0.51
     г
    0.50
    G
    0.50
     га
    0.49
    POSITIVE LOGITS
     Inu
    0.53
    Nun
    0.51
    inu
    0.49
    Nu
    0.49
     Nu
    0.48
    ইন
    0.48
    누
    0.47
     Nun
    0.46
     İn
    0.45
    nu
    0.45
    Activations Density 0.001%

    No Known Activations