© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58519
    Prev
    Next
    INDEX
    Explanations

    can't help but

    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_11_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
    ari
    0.72
    al
    0.71
    Imp
    0.71
     /
    0.68
      
    0.64
    lose
    0.63
    afka
    0.62
    LA
    0.61
    _
    0.61
    aut
    0.61
    POSITIVE LOGITS
     ironically
    0.64
     préalable
    0.57
     alcuni
    0.57
     bardziej
    0.57
     nedenle
    0.57
     apie
    0.56
     যন্ত্র
    0.56
     alcune
    0.55
     intitulé
    0.55
     unele
    0.55
    Activations Density 0.001%

    No Known Activations