© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 218159
    Prev
    Next
    INDEX
    Explanations

    metric units followed by nouns

    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_16_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
    கு
    0.56
     effector
    0.48
    {
    0.47
    По
    0.45
    소를
    0.45
    شو
    0.44
    어
    0.44
    دت
    0.44
    +')
    0.44
    د
    0.44
    POSITIVE LOGITS
     zindagi
    0.52
     Slate
    0.50
     Singapore
    0.48
     सिंगापुर
    0.48
     あなた
    0.47
    camore
    0.46
     教え
    0.46
     governed
    0.46
     situate
    0.46
    ខ្ញុំ
    0.46
    Activations Density 0.000%

    No Known Activations