© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45474
    Prev
    Next
    INDEX
    Explanations

    supposed to

    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_13_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
     ی
    0.55
    anded
    0.52
     tactics
    0.50
    ed
    0.49
     dificultades
    0.48
     attempted
    0.47
    es
    0.46
    arus
    0.46
    lasma
    0.46
    étrica
    0.46
    POSITIVE LOGITS
    淚
    0.48
    znacz
    0.47
    вість
    0.47
    鑼
    0.45
    高
    0.44
    저
    0.44
    净
    0.44
    lookup
    0.43
    ｔ
    0.43
    Lookup
    0.43
    Activations Density 0.000%

    No Known Activations