© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28847
    Prev
    Next
    INDEX
    Explanations

    send/get database host name

    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_40_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
     hooking
    0.45
    杀了
    0.39
     KILL
    0.38
    Execute
    0.38
    configure
    0.38
    估
    0.37
    estead
    0.37
    님이
    0.37
    拟
    0.37
     kill
    0.36
    POSITIVE LOGITS
     meri
    0.41
     cest
    0.41
     ['
    0.38
    TreeNode
    0.38
    蟀
    0.38
     ['',
    0.37
    笥
    0.36
     Mujer
    0.36
     continuant
    0.36
    琙
    0.36
    Activations Density 0.000%

    No Known Activations