© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90069
    Prev
    Next
    INDEX
    Explanations

    LM Studio and API clients

    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_3_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
     for
    0.83
    0
    0.80
     quyển
    0.70
     mất
    0.67
    6
    0.67
     allege
    0.66
     வண்ணப்பூச்சு
    0.66
     incorrectly
    0.65
    8
    0.64
     warm
    0.63
    POSITIVE LOGITS
    ו
    1.15
    ه
    1.05
    ف
    1.05
    د
    0.98
    و
    0.98
    ط
    0.97
    ح
    0.88
    ب
    0.86
    在
    0.84
    ש
    0.84
    Activations Density 0.003%

    No Known Activations