© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27501
    Prev
    Next
    INDEX
    Explanations

    easily

    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_10_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
    و
    0.48
    ان
    0.48
    -
    0.37
    {
    0.37
    <0x93>
    0.37
    ли
    0.36
    с
    0.36
    ار
    0.35
    ري
    0.35
    ٤
    0.35
    POSITIVE LOGITS
     for
    0.41
     factories
    0.41
     PRODU
    0.40
     asli
    0.40
     automation
    0.38
     externalities
    0.37
     GRA
    0.37
     antib
    0.36
     abduction
    0.36
     industries
    0.36
    Activations Density 0.008%

    No Known Activations