© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 209848
    Prev
    Next
    INDEX
    Explanations

    obstacles or barriers

    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_19_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
     tonight
    0.33
     اینجا
    0.31
     сюда
    0.30
    INFO
    0.29
    してください
    0.29
    _
    0.28
     desh
    0.28
     이곳
    0.28
    FROM
    0.27
    ни
    0.27
    POSITIVE LOGITS
    τός
    0.33
    ដែលមាន
    0.31
     மன
    0.30
    stellt
    0.30
     TestAvg
    0.30
     लिविंग
    0.30
    揍
    0.30
     ሕ
    0.29
    之心
    0.29
    EMANN
    0.29
    Activations Density 0.006%

    No Known Activations