© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49989
    Prev
    Next
    INDEX
    Explanations

    affectionate terms and terms of endearment

    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_31_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
    腌
    0.42
     ребята
    0.40
    oph
    0.38
    叔
    0.36
    ্লো
    0.36
     ребят
    0.35
    Ciao
    0.35
     نعمل
    0.35
     Barnes
    0.34
     Electrochemical
    0.34
    POSITIVE LOGITS
     overdose
    0.39
     spread
    0.37
     variables
    0.36
     spreads
    0.36
    ‏‏
    0.36
     simulations
    0.36
     simulation
    0.35
     cher
    0.35
     strikes
    0.35
    tson
    0.35
    Activations Density 0.018%

    No Known Activations