© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131389
    Prev
    Next
    INDEX
    Explanations

    held

    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_1_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
    in
    1.64
    ו
    1.53
    ين
    1.50
    ا
    1.44
    น
    1.27
    ة
    1.25
    та
    1.15
    ק
    1.12
    ing
    1.06
    ي
    1.05
    POSITIVE LOGITS
    ↵
    1.01
    amp
    0.95
     nostre
    0.95
     customization
    0.94
    ON
    0.94
     vede
    0.93
    ך
    0.92
     į
    0.90
    DE
    0.89
     customize
    0.88
    Activations Density 0.001%

    No Known Activations