© 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. 150577
    Prev
    Next
    INDEX
    Explanations

    type of code construct

    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
     仕事
    0.50
    漀
    0.49
    hus
    0.47
     كم
    0.47
    らが
    0.47
    糧
    0.47
    اردوش
    0.46
    悔
    0.46
    ៥
    0.45
     剤
    0.44
    POSITIVE LOGITS
    itecture
    0.52
     nella
    0.48
    ющимся
    0.47
     पसर
    0.45
    ométrie
    0.45
     görüntü
    0.44
    izados
    0.44
    циям
    0.42
     scrolled
    0.42
     nelle
    0.41
    Activations Density 0.000%

    No Known Activations