© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177478
    Prev
    Next
    INDEX
    Explanations

    saints historical figures

    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
    urlencoded
    0.40
    زين
    0.39
    SCs
    0.39
    جور
    0.38
    ሆነ
    0.36
    嗪
    0.36
    Ali
    0.35
    QB
    0.35
    rali
    0.35
    SizeMode
    0.34
    POSITIVE LOGITS
     जॉन
    0.43
    JOHN
    0.39
     कार्बो
    0.38
     waterline
    0.38
    рена
    0.38
    polls
    0.38
    퇴
    0.38
     saveData
    0.37
     john
    0.37
    ahas
    0.37
    Activations Density 0.000%

    No Known Activations