© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32399
    Prev
    Next
    INDEX
    Explanations

    list items or steps

    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
     rung
    0.40
     Morin
    0.39
    ঙ্ক
    0.38
     ቡ
    0.38
     sentiments
    0.38
     جیت
    0.38
    ását
    0.36
    会将
    0.36
     profundidad
    0.36
     means
    0.35
    POSITIVE LOGITS
    Selection
    0.44
    Lincoln
    0.41
    Therefore
    0.40
     Selection
    0.39
    Whereas
    0.39
    SEC
    0.38
    털
    0.38
    Sec
    0.38
     Now
    0.37
    Now
    0.37
    Activations Density 0.107%

    No Known Activations