© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206506
    Prev
    Next
    INDEX
    Explanations

    dark places

    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
    ཛ
    0.43
    ]){
    0.42
     coval
    0.40
     khắp
    0.39
    aków
    0.38
     जाए
    0.38
    lde
    0.38
    膊
    0.37
     throughout
    0.37
    '])){
    0.37
    POSITIVE LOGITS
    UL
    0.47
    Ephemeral
    0.47
    Alt
    0.46
     العمر
    0.46
    Tong
    0.46
     установка
    0.46
    oggetto
    0.44
     американский
    0.44
    Easing
    0.44
    Out
    0.43
    Activations Density 0.001%

    No Known Activations