© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50417
    Prev
    Next
    INDEX
    Explanations

    body parts

    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_30_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
    钝
    0.32
    cèle
    0.30
     peninsula
    0.30
    ceria
    0.29
    цна
    0.27
     পক্ষের
    0.27
     නිෂ්පා
    0.27
     полуо
    0.27
    ScreenWidth
    0.27
    ઠળ
    0.27
    POSITIVE LOGITS
    ನ್ಯ
    0.33
     hát
    0.31
     वैसा
    0.31
     interpretación
    0.30
    એ
    0.30
     முருகன்
    0.30
     "["
    0.30
    ANSAS
    0.30
     অসু
    0.29
    Ū
    0.29
    Activations Density 0.012%

    No Known Activations