© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 165811
    Prev
    Next
    INDEX
    Explanations

    if you

    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_34_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
    〠
    0.38
    ites
    0.37
    inks
    0.37
     squares
    0.36
     கழு
    0.35
     शिक्
    0.35
     rost
    0.35
    Ability
    0.35
    ClientSize
    0.35
    стями
    0.35
    POSITIVE LOGITS
    snippet
    0.39
     Succ
    0.38
    သ
    0.37
     ullamco
    0.36
    动力
    0.36
    塞
    0.35
     տ
    0.35
    如此
    0.35
     pärast
    0.35
     .^{
    0.34
    Activations Density 0.004%

    No Known Activations