© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214148
    Prev
    Next
    INDEX
    Explanations

    .deb, .docx, .NET, .pb file types

    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_5_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
    は
    1.20
    。"
    1.20
    ري
    1.17
    o
    1.02
    的技术
    0.99
    。
    0.97
    𝐨
    0.96
    اب
    0.95
    о
    0.95
    ">
    0.95
    POSITIVE LOGITS
    ?
    1.10
    et
    1.09
    it
    1.03
    kumar
    1.02
    >
    0.94
    gart
    0.93
    ットン
    0.93
    প্রাপ্ত
    0.90
    andolo
    0.88
    ptic
    0.87
    Activations Density 0.002%

    No Known Activations