© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140501
    Prev
    Next
    INDEX
    Explanations

    message in a bottle

    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_12_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
    f
    0.70
    
    0.64
    ations
    0.64
    I
    0.59
    ation
    0.57
    ığı
    0.57
    
    0.55
    gins
    0.54
    ület
    0.52
     विश्वविद्यालयों
    0.52
    POSITIVE LOGITS
     retirer
    0.63
    ра
    0.57
     prices
    0.55
     scorer
    0.53
    ك
    0.53
     assegn
    0.52
     trophy
    0.51
    נ
    0.51
    را
    0.51
     percentuale
    0.51
    Activations Density 0.000%

    No Known Activations