© 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. 33696
    Prev
    Next
    INDEX
    Explanations

    state power and control

    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
     prestación
    0.37
     طرح
    0.37
    システム
    0.36
     प्रशंसकों
    0.36
    Php
    0.36
    饥
    0.36
    Blow
    0.35
     Chirurgien
    0.35
    システムの
    0.35
     haut
    0.35
    POSITIVE LOGITS
    Brook
    0.41
     militias
    0.41
     Opus
    0.40
     Integrative
    0.40
     Brookfield
    0.40
     Voluntary
    0.39
    rola
    0.37
    狧
    0.37
     Polic
    0.37
     egyes
    0.37
    Activations Density 0.045%

    No Known Activations