© 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. 15401
    Prev
    Next
    INDEX
    Explanations

    =>

    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
    Low
    0.34
     l
    0.32
     low
    0.30
    cor
    0.28
    COR
    0.27
     )
    0.27
     Is
    0.26
     pe
    0.25
    low
    0.25
     ),
    0.25
    POSITIVE LOGITS
     jurispr
    0.29
    썼
    0.28
    Перед
    0.27
    썻
    0.26
     Agn
    0.26
    ланды
    0.26
     있었다
    0.26
     forskj
    0.25
     автомобиль
    0.25
    ्स
    0.25
    Activations Density 0.113%

    No Known Activations