© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199250
    Prev
    Next
    INDEX
    Explanations

    medical symptoms

    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
    žen
    0.45
     ફ
    0.40
    rep
    0.38
     Perse
    0.38
     máquina
    0.38
     noc
    0.38
    нику
    0.37
     case
    0.37
     caso
    0.37
     Burmese
    0.37
    POSITIVE LOGITS
    水
    0.41
    Water
    0.40
     اجر
    0.38
    开头
    0.38
    water
    0.38
    たく
    0.38
     Rowan
    0.37
    rainbow
    0.37
    ictus
    0.37
    gewater
    0.36
    Activations Density 0.001%

    No Known Activations