© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176884
    Prev
    Next
    INDEX
    Explanations

    seven, nine

    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_50_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
     Eighty
    1.62
     eighty
    1.53
    8
    1.46
     ۸
    1.30
     ८
    1.30
    ８
    1.28
     ৮০
    1.23
    
    1.17
     вось
    1.16
    ۸
    1.16
    POSITIVE LOGITS
    九
    0.68
    七
    0.55
     nine
    0.54
    Nine
    0.53
     Seven
    0.52
    Seven
    0.52
     Nine
    0.51
    seven
    0.49
     九
    0.49
    nine
    0.48
    Activations Density 0.009%

    No Known Activations