© 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. 5440
    Prev
    Next
    INDEX
    Explanations

    email correspondence

    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
    ♻
    0.42
     Республика
    0.42
     Expt
    0.40
     справед
    0.38
     Peaceful
    0.38
    葲
    0.38
    ikum
    0.38
    髖
    0.37
    隈
    0.37
    空氣
    0.37
    POSITIVE LOGITS
     correspondence
    0.66
    Correspondence
    0.59
    correspond
    0.57
     letter
    0.56
     letters
    0.55
     correspondences
    0.55
     corris
    0.55
    letter
    0.54
    letters
    0.53
     correspond
    0.53
    Activations Density 0.002%

    No Known Activations