© 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. 15705
    Prev
    Next
    INDEX
    Explanations

    "text" or 'text'

    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
     λέ
    0.17
     publishing
    0.16
     affidavit
    0.16
     "
    0.16
     потому
    0.16
     leading
    0.16
     मात्र
    0.16
     m
    0.16
     л
    0.16
     schooling
    0.16
    POSITIVE LOGITS
    errno
    0.20
    ün
    0.20
    first
    0.19
    जेक्ट
    0.18
    üng
    0.18
     germinate
    0.18
    முகம்
    0.18
    racción
    0.18
     bebê
    0.18
     manches
    0.17
    Activations Density 0.154%

    No Known Activations