© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85645
    Prev
    Next
    INDEX
    Explanations

    deacon, Secretary, Guardian, salt, sigmoid flexure

    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_18_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
    䙷
    0.50
     jotka
    0.50
    㕩
    0.49
    䛶
    0.48
     kuris
    0.46
     wych
    0.45
     amelyek
    0.44
     Valentino
    0.44
     Syk
    0.44
     Tabla
    0.43
    POSITIVE LOGITS
    斷
    0.46
     keltiradi
    0.45
    正在
    0.45
    圣
    0.45
    After
    0.43
     cushion
    0.43
    ဤ
    0.42
     embezz
    0.42
     lettering
    0.42
    संयुक्त
    0.42
    Activations Density 0.000%

    No Known Activations