© 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. 247177
    Prev
    Next
    INDEX
    Explanations

    send back

    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
     Greenland
    0.34
    university
    0.34
     Kelvin
    0.33
     Caring
    0.33
     university
    0.33
     voice
    0.33
     Greenway
    0.32
    힘
    0.32
    exit
    0.32
    Як
    0.32
    POSITIVE LOGITS
     send
    1.66
     Send
    1.61
    Send
    1.56
    send
    1.55
     sending
    1.53
     sends
    1.47
     Sending
    1.45
     보내
    1.43
     отправ
    1.42
     Sends
    1.38
    Activations Density 0.002%

    No Known Activations