© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164445
    Prev
    Next
    INDEX
    Explanations

    to find or predict

    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_31_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
     اخذ
    0.41
    ocking
    0.39
     تشکیل
    0.36
     আঞ্চলিক
    0.36
    CMake
    0.35
     красно
    0.35
    वाधिकार
    0.35
    𒈪
    0.35
    odies
    0.34
    codigo
    0.34
    POSITIVE LOGITS
     illustrating
    0.38
     Ren
    0.37
     عر
    0.36
    φέρον
    0.36
     facilitating
    0.35
     lieux
    0.35
    ियर
    0.35
     illumination
    0.35
     glaring
    0.35
     clarification
    0.35
    Activations Density 0.002%

    No Known Activations