© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173780
    Prev
    Next
    INDEX
    Explanations

    followed by a specific word

    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
    storage
    0.16
    ූප
    0.16
    str
    0.16
     convenc
    0.16
    notes
    0.15
    ዖ
    0.15
    exus
    0.15
     কাশ্ম
    0.15
    ഴി
    0.15
    cass
    0.15
    POSITIVE LOGITS
     Netflix
    0.20
     daughter
    0.17
     Από
    0.17
     Von
    0.17
    （
    0.17
    联合
    0.17
     Sion
    0.16
     mochila
    0.16
    昏
    0.16
     Für
    0.16
    Activations Density 0.000%

    No Known Activations