© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178298
    Prev
    Next
    INDEX
    Explanations

    currently

    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_24_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
     Controlador
    0.43
     Freighter
    0.36
     ഉപ
    0.36
     Sunday
    0.35
     Figure
    0.35
     Rick
    0.35
    鹕
    0.35
     Modes
    0.35
     Friday
    0.34
    ས
    0.34
    POSITIVE LOGITS
    需
    0.43
     immediatamente
    0.42
    immediately
    0.40
    eby
    0.38
     imedi
    0.38
     descrizione
    0.37
     imediat
    0.37
     imediatamente
    0.37
    ಜು
    0.36
    utive
    0.36
    Activations Density 0.005%

    No Known Activations