© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37457
    Prev
    Next
    INDEX
    Explanations

    abstract expressionism, abstract class

    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_3_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
    ة
    0.85
    い
    0.78
    يت
    0.77
    یت
    0.75
    د
    0.73
    ње
    0.70
    يط
    0.66
     élu
    0.65
    ü
    0.64
    ή
    0.63
    POSITIVE LOGITS
    ר
    0.93
    ার
    0.72
    er
    0.65
    ر
    0.62
    ay
    0.62
    anedi
    0.59
    ट्र
    0.57
    ার্স
    0.57
    erd
    0.57
    0
    0.55
    Activations Density 0.002%

    No Known Activations