© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49918
    Prev
    Next
    INDEX
    Explanations

    homology and -ology suffixes

    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_10_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
    يت
    0.71
     ။
    0.71
    م
    0.71
     repercussions
    0.69
    )$
    0.68
    نع
    0.68
    اس
    0.67
    )$.
    0.66
    것
    0.66
    ９
    0.65
    POSITIVE LOGITS
     in
    0.84
     da
    0.70
    durch
    0.69
    do
    0.68
     அல்லது
    0.65
    day
    0.64
     thậm
    0.64
    dated
    0.63
     or
    0.62
     d
    0.61
    Activations Density 0.004%

    No Known Activations