© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198607
    Prev
    Next
    INDEX
    Explanations

    non-production environmentrepresentative collectionrepresentative ofrepresentative examplerepresentative, a collectionrepresentative differentrepresentative of differentnon-production. This helpsrepresentative ofnon-productionrepresentative ofrepresentative

    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
    6
    0.27
    8
    0.23
    ug
    0.21
    0
    0.21
      
    0.21
    w
    0.21
    real
    0.21
    oser
    0.21
    к
    0.20
     and
    0.20
    POSITIVE LOGITS
     RasterModelGrid
    0.25
     mons
    0.23
    نىڭ
    0.21
    న్‌లో
    0.21
     সবগুলো
    0.21
    ன்றால்
    0.21
     Drei
    0.21
    groupBox
    0.21
     seules
    0.20
    tól
    0.20
    Activations Density 0.005%

    No Known Activations