© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12285
    Prev
    Next
    INDEX
    Explanations

    actuators and hydraulic cylinders

    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_13_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
     scenes
    0.36
     potřeb
    0.35
     multi
    0.33
    CLUSIVE
    0.33
     vikt
    0.31
     ਟ
    0.31
     obnov
    0.31
     moe
    0.31
     dest
    0.31
     headaches
    0.30
    POSITIVE LOGITS
    append
    0.32
    valley
    0.32
    CFBundle
    0.31
    āli
    0.31
     Pflanzen
    0.31
    databind
    0.31
     Neuen
    0.31
     Кстати
    0.31
    "?>
    0.30
    enties
    0.30
    Activations Density 0.007%

    No Known Activations