© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201166
    Prev
    Next
    INDEX
    Explanations

    file operations with open

    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_37_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
     писа
    0.44
     создал
    0.43
    书
    0.42
     yazı
    0.41
    を書
    0.40
     书
    0.40
     loại
    0.39
    書
    0.39
     textArea
    0.38
     Portfolio
    0.38
    POSITIVE LOGITS
    AppLink
    0.37
    ܩ
    0.37
    Ἄ
    0.37
     underpin
    0.36
    ITU
    0.36
    ጌ
    0.36
     inelastic
    0.35
    นุ
    0.35
    omicron
    0.35
     inodes
    0.34
    Activations Density 0.006%

    No Known Activations