© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43189
    Prev
    Next
    INDEX
    Explanations

    agape

    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_3_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
    ك
    0.80
     que
    0.74
     junge
    0.73
    :
    0.70
     strung
    0.70
     grosse
    0.69
     constru
    0.69
     bestimmte
    0.68
     nette
    0.68
    ()}
    0.68
    POSITIVE LOGITS
    ut
    0.83
    ри
    0.79
     Moldova
    0.77
    od
    0.76
    ponsorship
    0.76
     Affordable
    0.73
    li
    0.70
    اک
    0.69
     Oncology
    0.68
    п
    0.66
    Activations Density 0.002%

    No Known Activations