© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134649
    Prev
    Next
    INDEX
    Explanations

    how people met

    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_37_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
     салу
    0.37
     Indexed
    0.37
    Snow
    0.36
    Flask
    0.36
    莫
    0.36
    Ext
    0.35
     Neur
    0.34
    .')
    0.34
    蚪
    0.34
    uddh
    0.34
    POSITIVE LOGITS
     meet
    1.85
     met
    1.68
     Meet
    1.68
    meet
    1.67
    Meet
    1.66
     meets
    1.64
     bertemu
    1.56
     встре
    1.55
     встреча
    1.45
     MEET
    1.44
    Activations Density 0.004%

    No Known Activations