© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14618
    Prev
    Next
    INDEX
    Explanations

    paint, colors, painting

    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
    October
    0.50
     flapping
    0.48
    "
    0.47
    )."
    0.46
    :[/
    0.46
     inquest
    0.46
     october
    0.46
    "。
    0.46
     ."
    0.45
     deflate
    0.45
    POSITIVE LOGITS
     Filho
    0.50
    YPE
    0.48
    èle
    0.46
    textfield
    0.45
    ą
    0.45
    ando
    0.45
    자가
    0.45
    ând
    0.44
    eração
    0.44
    ază
    0.44
    Activations Density 0.010%

    No Known Activations