© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215908
    Prev
    Next
    INDEX
    Explanations

    AI and technology

    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_50_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
    jasper
    0.41
     बीएस
    0.38
    щик
    0.38
     Jasper
    0.38
     яви
    0.37
    стон
    0.36
     শের
    0.36
    
    0.36
     جات
    0.36
     multiplets
    0.35
    POSITIVE LOGITS
     Pro
    0.45
    プラ
    0.44
     PTC
    0.43
     Cob
    0.42
     الم
    0.42
     M
    0.41
    エン
    0.41
    甜
    0.41
    ક્
    0.41
     ラン
    0.41
    Activations Density 0.054%

    No Known Activations