© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52680
    Prev
    Next
    INDEX
    Explanations

    which or latter

    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_31_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
     envie
    0.33
     cultivo
    0.33
     Maser
    0.33
     bomber
    0.32
     itaque
    0.32
     cultivés
    0.32
     insufficiency
    0.31
    ︵
    0.31
    ंदरे
    0.31
     peritoneal
    0.30
    POSITIVE LOGITS
     Patch
    0.33
    aided
    0.32
    伶
    0.32
     Director
    0.31
     Comp
    0.30
     Press
    0.30
    Press
    0.30
     Detroit
    0.30
     Madison
    0.30
    机制
    0.30
    Activations Density 0.003%

    No Known Activations