© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141890
    Prev
    Next
    INDEX
    Explanations

    metallic colors and textures

    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_12_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
    лове
    0.55
    ím
    0.53
     mosa
    0.51
    <0xAC>
    0.50
    <
    0.50
    र्स
    0.48
     siège
    0.48
    ious
    0.48
     сло
    0.48
    abilités
    0.47
    POSITIVE LOGITS
    assertEqual
    0.57
     Journals
    0.56
     Bachchan
    0.55
     ਵ
    0.55
     Airways
    0.54
     richtigen
    0.52
    پردا
    0.52
     Upan
    0.52
    えて
    0.51
     Entertain
    0.51
    Activations Density 0.000%

    No Known Activations