© 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. 18192
    Prev
    Next
    INDEX
    Explanations

    regions, malt, ABA codes

    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
    A
    0.51
    E
    0.48
    ハイ
    0.46
    Rak
    0.44
    we
    0.43
     ordinairement
    0.43
    ڍ
    0.43
    傢
    0.43
     hesab
    0.43
    संयुक्त
    0.42
    POSITIVE LOGITS
     JAN
    0.52
    uğu
    0.49
    edal
    0.47
     ASM
    0.44
    "].
    0.44
    들도
    0.44
    enças
    0.43
    duğu
    0.43
     universities
    0.43
     victories
    0.43
    Activations Density 0.019%

    No Known Activations