© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    4. 4571
    Prev
    Next
    INDEX
    Explanations

    document.getElementById or related

    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
     黄
    0.38
     結果
    0.37
    colgroup
    0.36
    မာ
    0.36
     pa
    0.35
    aranja
    0.35
    湪
    0.35
    igian
    0.35
    事前
    0.35
    Kirk
    0.34
    POSITIVE LOGITS
    getElement
    0.43
     element
    0.40
     findAll
    0.40
     fluctuates
    0.39
    findAll
    0.38
    URNS
    0.38
     allocates
    0.38
     Limitation
    0.37
     crest
    0.37
    <?=$
    0.37
    Activations Density 0.010%

    No Known Activations