© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 68583
    Prev
    Next
    INDEX
    Explanations

    clad, iPad, Vad

    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_51_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
     grossesse
    0.39
    
    0.39
     singleRun
    0.39
    敒
    0.38
     consumo
    0.38
     karta
    0.37
     baya
    0.37
    hyperref
    0.37
    꺽
    0.37
     قوي
    0.37
    POSITIVE LOGITS
    Vad
    1.96
    vad
    1.95
     Vad
    1.93
     vad
    1.91
     Wad
    1.77
    wad
    1.76
     Jad
    1.75
     wad
    1.70
    tad
    1.67
     Tad
    1.66
    Activations Density 0.018%

    No Known Activations