© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49274
    Prev
    Next
    INDEX
    Explanations

    uncertainty, toggle

    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_10_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
     livid
    0.15
    <0x80>
    0.14
     vutto
    0.13
     Helmholtz
    0.13
    ান্দ
    0.13
     遅く
    0.12
     Leibniz
    0.12
     kē
    0.12
    OpenJDK
    0.12
     thawed
    0.12
    POSITIVE LOGITS
    uct
    0.13
    k
    0.13
    kala
    0.13
    fic
    0.13
     बीमा
    0.12
    kraft
    0.12
    kje
    0.12
     komplette
    0.12
    ن
    0.12
    이나
    0.12
    Activations Density 0.023%

    No Known Activations