© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180906
    Prev
    Next
    INDEX
    Explanations

    places after "Depart"

    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
    趾
    0.16
    频谱
    0.16
     スペ
    0.16
     मुद्दों
    0.15
    诘
    0.15
    (-\
    0.15
    beginPath
    0.15
    郸
    0.15
     suffering
    0.15
     চক্ষু
    0.15
    POSITIVE LOGITS
     gypsy
    0.16
    kolah
    0.16
     vandalism
    0.16
     railway
    0.15
     nguyện
    0.15
     gy
    0.15
     municipal
    0.15
     cháu
    0.14
     sacr
    0.14
    overl
    0.14
    Activations Density 0.001%

    No Known Activations