© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43859
    Prev
    Next
    INDEX
    Explanations

    but contrast connector

    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_13_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
     бір
    0.40
    as
    0.39
    숫
    0.38
    ere
    0.37
     خلال
    0.37
     هذا
    0.36
     bahawa
    0.35
    かつ
    0.35
     conosci
    0.34
     Flughafen
    0.34
    POSITIVE LOGITS
     like
    0.36
    usions
    0.34
     ostr
    0.34
    Monty
    0.34
    
    0.34
     behaviors
    0.33
     robes
    0.33
     have
    0.33
    ryst
    0.33
    NEEDED
    0.32
    Activations Density 0.035%

    No Known Activations