© 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. 196168
    Prev
    Next
    INDEX
    Explanations

    Pedialyte

    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
     apricots
    0.42
    Clock
    0.40
    Caro
    0.39
     लिविंग
    0.39
     L
    0.38
     levi
    0.38
    Levi
    0.38
     eroded
    0.38
    Tend
    0.38
    ہوں
    0.38
    POSITIVE LOGITS
    біт
    0.41
     уг
    0.37
    跖
    0.37
    ヨン
    0.36
    adee
    0.36
     molecular
    0.36
    elj
    0.36
     выбра
    0.35
    elb
    0.35
     обре
    0.34
    Activations Density 0.002%

    No Known Activations