© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126059
    Prev
    Next
    INDEX
    Explanations

    emergent abilities or capability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
    vegarde
    0.40
    癤
    0.40
     المصطلح
    0.38
    卸
    0.38
    PopMatrix
    0.38
     胸
    0.37
     পর্ব
    0.35
    飏
    0.35
     remport
    0.35
    ﮟ
    0.34
    POSITIVE LOGITS
    template
    0.68
     template
    0.68
    Template
    0.66
     templates
    0.63
     шаблон
    0.63
     formatted
    0.62
     Template
    0.60
    formatted
    0.58
     Templates
    0.58
     шабло
    0.57
    Activations Density 0.009%

    No Known Activations