© 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. 153755
    Prev
    Next
    INDEX
    Explanations

    round

    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
    3
    0.71
    4
    0.70
    5
    0.64
    1
    0.62
    9
    0.58
    ۴
    0.55
    8
    0.55
    ３
    0.54
    ４
    0.54
    ۱۰
    0.52
    POSITIVE LOGITS
     round
    2.80
    Round
    2.55
     Round
    2.52
    round
    2.48
     ROUND
    2.25
    ROUND
    2.05
     राउंड
    1.89
    ラウンド
    1.75
     круг
    1.75
     rond
    1.74
    Activations Density 0.007%

    No Known Activations