© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16146
    Prev
    Next
    INDEX
    Explanations

    materials like wood, porcelain, glass, stone

    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_15_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
    音频
    0.53
    UMNS
    0.49
     phenomena
    0.49
    TD
    0.48
    Videos
    0.47
     responses
    0.47
     videos
    0.46
    为
    0.46
    <div>
    0.45
     영상을
    0.45
    POSITIVE LOGITS
     Özel
    0.54
     Jé
    0.52
     OFFSET
    0.49
     ISC
    0.49
     Couleur
    0.48
     vorbe
    0.48
    primir
    0.47
     оф
    0.47
     ITC
    0.46
     ماشینونه
    0.46
    Activations Density 0.028%

    No Known Activations