© 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. 18278
    Prev
    Next
    INDEX
    Explanations

    model kits or hobby 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_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
    shu
    0.40
     опу
    0.38
     συμφ
    0.38
    udarstvennyj
    0.37
    External
    0.36
    ]];
    0.36
     이차
    0.36
    Vertex
    0.35
    areader
    0.35
     dehumid
    0.35
    POSITIVE LOGITS
    formula
    0.41
     molecules
    0.38
    плення
    0.38
    oring
    0.38
     탱크
    0.38
     SLOT
    0.38
    resso
    0.37
     pancre
    0.37
    グループ
    0.36
    组
    0.36
    Activations Density 0.035%

    No Known Activations