© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 214672
    Prev
    Next
    INDEX
    Explanations

    cry

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
    涙
    0.77
     tears
    0.77
     Tears
    0.72
     Tear
    0.70
     tear
    0.66
    泪
    0.66
    淚
    0.62
    tear
    0.58
     sobbing
    0.58
     weeping
    0.57
    POSITIVE LOGITS
     autoridades
    0.43
     lè
    0.42
     HINSTANCE
    0.38
     হত্যার
    0.38
    insch
    0.38
    ève
    0.38
    urna
    0.37
     hablando
    0.37
    գ
    0.37
     autoridad
    0.37
    Activations Density 0.000%

    No Known Activations