© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69267
    Prev
    Next
    INDEX
    Explanations

    conversational reflection

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Hm
    0.59
     hm
    0.57
     HM
    0.52
     hmm
    0.52
    嗯
    0.50
     Hmm
    0.47
    hm
    0.47
     Somebody
    0.45
    Hm
    0.43
    ウム
    0.42
    POSITIVE LOGITS
    good
    0.43
     टच
    0.40
     क्यूट
    0.40
    वा
    0.39
    MULTI
    0.39
     nField
    0.39
    Field
    0.39
    
    0.39
     sapp
    0.38
     টেনে
    0.38
    Activations Density 0.002%

    No Known Activations