© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204732
    Prev
    Next
    INDEX
    Explanations

    `dropna`

    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_25_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
    არგ
    0.41
     भूटान
    0.39
     स्रो
    0.37
    สัม
    0.35
    ষণ
    0.35
     Switzerland
    0.35
     භ
    0.35
    姑娘
    0.35
    Swiss
    0.35
    श्मीर
    0.35
    POSITIVE LOGITS
    '[
    0.42
    Bec
    0.41
     Бек
    0.41
    ôi
    0.39
     Councilor
    0.39
    esinde
    0.37
     Bec
    0.37
     প্রশাসক
    0.37
     calyc
    0.36
     алы
    0.36
    Activations Density 0.001%

    No Known Activations