© 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. 195375
    Prev
    Next
    INDEX
    Explanations

    "one was", "back up", "little programming"

    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
    Յ
    0.57
    يل
    0.56
    ял
    0.53
    伊
    0.52
     ग्रोथ
    0.52
    ين
    0.51
     Sometimes
    0.51
    ياً
    0.51
    Я
    0.50
    ్య
    0.49
    POSITIVE LOGITS
    burn
    0.57
    br
    0.55
    transaction
    0.52
    formats
    0.51
    ados
    0.51
    če
    0.50
     affiliations
    0.50
    rež
    0.48
     commission
    0.48
     karan
    0.48
    Activations Density 0.000%

    No Known Activations