© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39671
    Prev
    Next
    INDEX
    Explanations

    Network Address Translation

    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_3_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
    지
    0.97
    и
    0.96
    ו
    0.92
    ą
    0.82
    де
    0.80
    u
    0.80
    ми
    0.80
    та
    0.79
    5
    0.74
    ະ
    0.73
    POSITIVE LOGITS
    BR
    0.62
    ichtig
    0.59
    ಾಗುತ್ತದೆ
    0.59
    ull
    0.59
    াত্র
    0.58
     Spiegel
    0.58
    BE
    0.57
    LLDB
    0.57
    ాన
    0.56
     दाब
    0.55
    Activations Density 0.004%

    No Known Activations