© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9889
    Prev
    Next
    INDEX
    Explanations

    expand call

    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
     поради
    0.26
    extern
    0.25
    rimination
    0.25
    ocentric
    0.25
    
    0.24
    ссмо
    0.23
     exercer
    0.23
    غم
    0.23
     ⚫
    0.23
     જેના
    0.22
    POSITIVE LOGITS
     buds
    0.28
     rape
    0.27
     studs
    0.27
    šli
    0.27
    दर
    0.26
     frau
    0.26
     dein
    0.25
     monsieur
    0.25
    ^{*}+
    0.25
     निर्माता
    0.25
    Activations Density 0.039%

    No Known Activations