© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6430
    Prev
    Next
    INDEX
    Explanations

    recent form and results

    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_40_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
    ="_
    0.40
    ==="
    0.39
    accessdate
    0.39
     سب
    0.39
    ?>"
    0.38
     গুলি
    0.38
     адрес
    0.37
    ='/'
    0.36
    товый
    0.36
     ?>"
    0.36
    POSITIVE LOGITS
     Gir
    0.43
     Moroccan
    0.41
    Hug
    0.41
    Gir
    0.40
    Double
    0.39
     organiser
    0.39
    াজন
    0.39
    Prés
    0.38
     Double
    0.38
     Tunisian
    0.38
    Activations Density 0.006%

    No Known Activations