© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61694
    Prev
    Next
    INDEX
    Explanations

    eosinophil, Hoisin, osimertinib, sarcoma

    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_2_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
    ي
    1.47
     Treiber
    1.34
    ן
    1.34
    ের
    1.25
    dır
    1.20
     طريق
    1.20
     authenticate
    1.19
     volant
    1.19
    ﺕ
    1.19
     propagate
    1.16
    POSITIVE LOGITS
    ong
    1.89
    r
    1.66
    ре
    1.52
    on
    1.47
    im
    1.44
    ack
    1.42
    وم
    1.37
    ing
    1.36
    ä
    1.32
    ed
    1.30
    Activations Density 0.000%

    No Known Activations