© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 153117
    Prev
    Next
    INDEX
    Explanations

    number 3

    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
    5
    1.07
    6
    0.84
     five
    0.82
     फाइव
    0.82
     Five
    0.79
     ५
    0.79
    ５
    0.79
    
    0.76
    ₅
    0.75
    ۵
    0.75
    POSITIVE LOGITS
    𝟯
    0.61
    0.59
    ۳
    0.57
    3
    0.56
    <0xBB>
    0.55
    𝟑
    0.55
    ３
    0.55
     ३
    0.52
     ۳
    0.52
    ३
    0.52
    Activations Density 0.014%

    No Known Activations