© 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. 155114
    Prev
    Next
    INDEX
    Explanations

    <

    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
    𝑃
    0.41
     chuck
    0.41
    𝐶
    0.40
     chauss
    0.40
    চ্ছন্দ
    0.40
    炀
    0.40
    িস্থ
    0.40
     photochemical
    0.40
    挲
    0.39
     chloroplast
    0.38
    POSITIVE LOGITS
    net
    0.44
    ertal
    0.42
    aska
    0.42
     ар
    0.39
     Hussein
    0.39
    棍
    0.39
     Ernesto
    0.38
     ارب
    0.37
    exe
    0.37
     MTN
    0.37
    Activations Density 0.002%

    No Known Activations