© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6988
    Prev
    Next
    INDEX
    Explanations

    explanation

    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
    atthena
    0.39
    leva
    0.39
    码
    0.37
     heraus
    0.37
    চ্ছন্ন
    0.37
    pocket
    0.36
    interrupt
    0.36
    寫
    0.36
    resist
    0.35
    anjutan
    0.35
    POSITIVE LOGITS
     perform
    0.44
     performs
    0.44
     لط
    0.40
     Perform
    0.39
     special
    0.39
     aqueous
    0.38
     specials
    0.38
     oxidant
    0.38
     Responsible
    0.37
    प्रेशन
    0.37
    Activations Density 0.181%

    No Known Activations