© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5023
    Prev
    Next
    INDEX
    Explanations

    java stream Collectors

    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_39_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
    肐
    0.43
    பிலோ
    0.43
    PHY
    0.42
     homologs
    0.41
     સાર
    0.39
    ℚ
    0.39
    υσ
    0.38
    ފ
    0.38
     Markets
    0.38
    ण्य
    0.38
    POSITIVE LOGITS
    attack
    0.40
    concurrent
    0.38
    application
    0.37
     hota
    0.36
     attacked
    0.36
    Collapse
    0.36
    event
    0.36
     potion
    0.36
    collapse
    0.35
     narrow
    0.35
    Activations Density 0.001%

    No Known Activations