© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199353
    Prev
    Next
    INDEX
    Explanations

    quote marks

    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_15_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
    
    0.26
    bs
    0.26
    cdn
    0.26
    have
    0.25
    video
    0.23
    we
    0.23
    don
    0.23
       
    0.23
    ј
    0.23
     Zahl
    0.22
    POSITIVE LOGITS
     precession
    0.26
     erreur
    0.25
     точку
    0.25
     layouts
    0.24
     intoler
    0.24
     énon
    0.23
     arrogance
    0.23
     notoriety
    0.23
     decontamination
    0.23
     chipping
    0.23
    Activations Density 0.001%

    No Known Activations