© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3346
    Prev
    Next
    INDEX
    Explanations

    stop words

    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_39_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
    正是
    0.46
    NotDefined
    0.39
     Cora
    0.39
     कमि
    0.38
    жаем
    0.38
    裟
    0.38
     Deed
    0.38
     كور
    0.37
    ått
    0.37
    𝚐
    0.37
    POSITIVE LOGITS
     emitted
    0.40
     malfunction
    0.39
    mein
    0.39
     processes
    0.38
     malfunctions
    0.38
     breezes
    0.38
    ه‌ای
    0.38
     metallic
    0.38
     indented
    0.37
     whole
    0.37
    Activations Density 0.009%

    No Known Activations