© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242430
    Prev
    Next
    INDEX
    Explanations

    saying goodbye or sending off

    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
    ទេស
    0.36
    opr
    0.34
    ﮈ
    0.34
    旬
    0.34
     움직
    0.33
    敖
    0.33
     ترى
    0.33
    ϩ
    0.32
     விஷய
    0.32
     místě
    0.32
    POSITIVE LOGITS
     send
    2.02
     Send
    1.84
    send
    1.83
    Send
    1.78
     farewell
    1.55
    送
    1.52
    SEND
    1.48
     sending
    1.47
     sends
    1.42
     Sending
    1.38
    Activations Density 0.032%

    No Known Activations