© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218083
    Prev
    Next
    INDEX
    Explanations

    code comments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
     ৭৮
    0.35
     Sixteen
    0.35
     tro
    0.34
    十六
    0.34
    Tamil
    0.33
    栉
    0.33
    hteet
    0.33
    പാ
    0.32
    Pn
    0.32
    尾
    0.32
    POSITIVE LOGITS
    cheiden
    0.40
    ভাষায়
    0.38
    oblasts
    0.38
    陏
    0.38
     Ramona
    0.38
     acaso
    0.38
     ഭക്ഷണം
    0.37
    detector
    0.37
    ម្ល
    0.37
     masuk
    0.37
    Activations Density 0.011%

    No Known Activations