© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12609
    Prev
    Next
    INDEX
    Explanations

    font design software and tools

    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_13_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
     resultant
    0.50
     vulture
    0.50
     tourne
    0.50
     Allah
    0.50
    👳
    0.49
     riche
    0.48
     preside
    0.48
    }${
    0.47
     creativa
    0.47
    gano
    0.47
    POSITIVE LOGITS
    ắp
    0.47
    OCE
    0.47
     সুবিধ
    0.47
    Chiều
    0.46
    মু
    0.46
     Swansea
    0.46
     index
    0.46
     Huddersfield
    0.46
    if
    0.45
    DEL
    0.45
    Activations Density 0.002%

    No Known Activations