© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43012
    Prev
    Next
    INDEX
    Explanations

    negation prefix

    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
    xlsx
    0.40
    interests
    0.38
    ircon
    0.36
    ids
    0.34
    Methylsulfanyl
    0.34
    舎
    0.34
    ire
    0.34
    way
    0.33
    kim
    0.33
    indazole
    0.33
    POSITIVE LOGITS
     AP
    0.38
     donning
    0.37
         
    0.36
       
    0.34
             
    0.34
     AN
    0.34
    㳒
    0.33
          
    0.32
     Garnier
    0.32
     COACH
    0.32
    Activations Density 0.051%

    No Known Activations