© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109750
    Prev
    Next
    INDEX
    Explanations

    Eher or honorable prefixes

    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_2_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
    る
    1.55
    at
    1.42
    고
    1.38
    ра
    1.34
    ר
    1.23
    س
    1.22
    <0x80>
    1.14
    त
    1.14
    ス
    1.12
    ת
    1.11
    POSITIVE LOGITS
     innovations
    0.92
     inroads
    0.90
     inclinations
    0.86
     imperatives
    0.84
     norms
    0.84
     demonstrations
    0.83
    lemente
    0.82
     hypersurfaces
    0.82
     transducers
    0.82
     indicators
    0.82
    Activations Density 0.001%

    No Known Activations