© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8132
    Prev
    Next
    INDEX
    Explanations

    Khan Academy math/science URLs

    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_40_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
    PNG
    0.38
    ucc
    0.38
    ステンレス
    0.37
    咙
    0.37
    (":
    0.36
     "{
    0.36
    fern
    0.35
    фер
    0.35
    ρύ
    0.35
    ,"$
    0.35
    POSITIVE LOGITS
    ឆ្ល
    0.40
     Detention
    0.40
     detention
    0.39
    ◸
    0.39
     indenture
    0.39
     unbounded
    0.38
    Columns
    0.38
     कम्पनी
    0.38
     বিদ্ব
    0.38
     scholar
    0.38
    Activations Density 0.001%

    No Known Activations