© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171347
    Prev
    Next
    INDEX
    Explanations

    any [request for information]

    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_20_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
    cribes
    0.38
     how
    0.36
     सरकारी
    0.35
    ーク
    0.34
    ある
    0.34
     hace
    0.33
    iremos
    0.33
     អ
    0.32
     conflicts
    0.31
    how
    0.31
    POSITIVE LOGITS
    тора
    0.36
     Kwiat
    0.32
     கட்டடக்கலை
    0.32
    倝
    0.32
     কাপুর
    0.31
     nervoso
    0.31
     Flam
    0.30
     šť
    0.30
    💡
    0.30
     importantes
    0.30
    Activations Density 0.002%

    No Known Activations