© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 88227
    Prev
    Next
    INDEX
    Explanations

    comes down to

    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_18_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
     genoemd
    0.52
     rearview
    0.52
    ６
    0.47
     skirting
    0.46
     പറഞ്ഞു
    0.46
     ඔවුන්
    0.46
     соответствует
    0.43
     őket
    0.43
     он
    0.42
    ？
    0.42
    POSITIVE LOGITS
    惭
    0.47
    綪
    0.46
    Over
    0.45
    amel
    0.45
    <strong>
    0.44
    Ret
    0.43
    자가
    0.43
    ของการ
    0.43
    <b>
    0.42
     over
    0.42
    Activations Density 0.001%

    No Known Activations