© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79670
    Prev
    Next
    INDEX
    Explanations

    title or position

    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_31_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
    opatra
    0.41
     ประเทศ
    0.40
    ড়াল
    0.39
    開業
    0.36
    졔
    0.35
     وزير
    0.35
    ୀ
    0.35
    櫃
    0.34
    Ⴝ
    0.34
     ಕೊಟ್ಟ
    0.34
    POSITIVE LOGITS
     sauve
    0.39
    明日
    0.37
    getSeconds
    0.35
     inmobili
    0.35
    Retrieve
    0.34
    Substitute
    0.34
    看不
    0.34
    rtle
    0.34
    crim
    0.34
    ப்புக்
    0.33
    Activations Density 0.001%

    No Known Activations