© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    4. 209052
    Prev
    Next
    INDEX
    Explanations

    I'll do that

    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_19_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
    डेंट
    0.47
    د
    0.47
     Photographic
    0.45
    <td>
    0.43
    ସ
    0.40
    冕
    0.39
    发布的
    0.39
    返
    0.39
    ﺪ
    0.39
    actionBarTab
    0.38
    POSITIVE LOGITS
     dice
    0.61
     Dice
    0.49
     lashes
    0.45
     봐야
    0.45
    েবে
    0.44
    Dice
    0.44
     kot
    0.44
     તમારે
    0.44
     koj
    0.43
     необхідно
    0.43
    Activations Density 0.002%

    No Known Activations