© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 183084
    Prev
    Next
    INDEX
    Explanations

    INTJ personality type Architects

    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_29_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
     چاہتا
    0.36
    咀
    0.36
     reassure
    0.35
    幵
    0.35
     रामचंद्र
    0.35
    筤
    0.34
    اضره
    0.33
     продукт
    0.33
     පෙ
    0.33
    maxage
    0.33
    POSITIVE LOGITS
    чис
    0.41
     gor
    0.40
    BufferedReader
    0.39
    iky
    0.38
     ख
    0.37
    Here
    0.37
    its
    0.37
     Worked
    0.36
    ယ်
    0.36
     Here
    0.36
    Activations Density 0.002%

    No Known Activations