© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198050
    Prev
    Next
    INDEX
    Explanations

    publicly funded accessible code injection

    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
    现在
    0.51
    ة
    0.50
     secretos
    0.49
    ائف
    0.47
    現在
    0.47
     frecuente
    0.46
    س
    0.46
    ف
    0.45
    يئة
    0.44
    ن
    0.43
    POSITIVE LOGITS
    ณา
    0.50
    wa
    0.47
     சூழ
    0.47
    spreadsheet
    0.45
    ขน
    0.44
     вен
    0.44
    ration
    0.44
     onslaught
    0.43
     चालीस
    0.43
    drawing
    0.43
    Activations Density 0.000%

    No Known Activations