© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93175
    Prev
    Next
    INDEX
    Explanations

    recipe data

    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_60_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
    2
    1.00
    <0x91>
    0.97
     twenty
    0.97
     Twenty
    0.85
     двадцать
    0.85
    Twenty
    0.78
     ۲
    0.77
     ၂
    0.73
    二十
    0.73
    ۲
    0.73
    POSITIVE LOGITS
    tw
    0.50
    Tw
    0.48
     ৩৫
    0.47
     Tw
    0.44
     tw
    0.42
    ３
    0.39
     छत्तीस
    0.39
    
    0.38
     ৩
    0.38
    Twig
    0.38
    Activations Density 0.025%

    No Known Activations