© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 16252
    Prev
    Next
    INDEX
    Explanations

    forest

    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
     tuku
    0.41
     Kram
    0.41
    三十
    0.38
    三百
    0.37
     Paise
    0.37
    ﮅ
    0.36
    oflavin
    0.36
    ataan
    0.35
    ોર્
    0.35
    まい
    0.35
    POSITIVE LOGITS
     قط
    0.41
    🍃
    0.40
    ❛
    0.37
     القط
    0.37
     buf
    0.37
     কন্যা
    0.36
    zani
    0.34
     REPLY
    0.34
    벌
    0.34
    Rel
    0.33
    Activations Density 0.019%

    No Known Activations