© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4195
    Prev
    Next
    INDEX
    Explanations

    words starting with letter

    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_40_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
     encounters
    0.36
    leigh
    0.34
     ออนไลน์
    0.34
    ोरेंट
    0.33
    <unused60>
    0.33
     Cooley
    0.33
    щён
    0.32
    हीं
    0.32
    டையே
    0.32
    icherweise
    0.32
    POSITIVE LOGITS
    Post
    0.36
     darbo
    0.35
    Canon
    0.34
     эш
    0.34
    ɠ
    0.34
     Dyna
    0.33
     trabajo
    0.33
     canon
    0.33
    +...+
    0.32
     nha
    0.32
    Activations Density 0.005%

    No Known Activations