© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100091
    Prev
    Next
    INDEX
    Explanations

    streamlit st.write and st.image

    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_14_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
     devised
    0.54
     scandal
    0.53
     desaparecido
    0.53
     gospod
    0.50
    avascript
    0.49
     dispar
    0.49
    𝗎
    0.49
     अध्ययन
    0.49
     antagon
    0.49
     Scandal
    0.49
    POSITIVE LOGITS
    ；
    0.54
    棪
    0.52
     dilute
    0.51
    ЕН
    0.51
    ീല
    0.50
    element
    0.50
    メント
    0.50
    ๛
    0.49
    刘
    0.49
     ایل
    0.48
    Activations Density 0.001%

    No Known Activations