© 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. 3525
    Prev
    Next
    INDEX
    Explanations

    javascript and IP addresses

    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
    மல்ல
    0.42
    Touches
    0.40
    歿
    0.37
    collections
    0.37
    lass
    0.36
     अधीनस्थों
    0.35
    遒
    0.35
     ይሰ
    0.34
    表面
    0.34
     በኋላ
    0.34
    POSITIVE LOGITS
     IP
    0.93
    IP
    0.76
     आईपी
    0.75
    ipfs
    0.74
     ip
    0.72
     Ip
    0.68
     IPM
    0.68
     IPs
    0.66
     IPF
    0.65
     IPC
    0.60
    Activations Density 0.178%

    No Known Activations