© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11756
    Prev
    Next
    INDEX
    Explanations

    pigment, color,inks

    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_40_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
     दुरु
    0.42
     dessins
    0.40
     drawings
    0.39
    枚
    0.37
     dessin
    0.36
    ޕ
    0.36
    Numerator
    0.36
    绘制
    0.36
    㛣
    0.36
     Drawings
    0.35
    POSITIVE LOGITS
     pigment
    1.07
     pigments
    1.03
     Pig
    0.94
     pigmentation
    0.92
    pig
    0.91
    Pig
    0.88
     pigmented
    0.87
     pig
    0.71
     pigs
    0.56
    色素
    0.55
    Activations Density 0.092%

    No Known Activations