© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49861
    Prev
    Next
    INDEX
    Explanations

    numbers

    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_55_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
     XVII
    0.61
    XVII
    0.57
     seventeenth
    0.55
     七
    0.54
     সপ্ত
    0.53
     १७
    0.53
    十七
    0.52
     hept
    0.50
    ⑦
    0.50
    <0xB3>
    0.49
    POSITIVE LOGITS
     ১৪
    0.51
     నాలుగు
    0.50
     fifth
    0.50
     четы
    0.49
    十四章
    0.48
    <unused94>
    0.47
     നാല
    0.47
     fourth
    0.46
     пя
    0.46
     four
    0.46
    Activations Density 0.102%

    No Known Activations