© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16392
    Prev
    Next
    INDEX
    Explanations

    park

    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
    ારા
    0.40
     passenger
    0.39
     follows
    0.39
     snowflake
    0.39
    룺
    0.38
     skiing
    0.38
     ヤ
    0.37
     visual
    0.37
     sightseeing
    0.37
    त्ती
    0.37
    POSITIVE LOGITS
     ر
    0.50
     r
    0.42
    м
    0.41
    -
    0.40
    sg
    0.39
     Pak
    0.39
     شكل
    0.39
    ien
    0.38
     ---
    0.38
     র
    0.38
    Activations Density 0.007%

    No Known Activations