© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13983
    Prev
    Next
    INDEX
    Explanations

    wooded swamps and forests

    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_40_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
    страи
    0.37
    เสียง
    0.36
    駐
    0.35
     initWithFrame
    0.33
     সম্পর্ক
    0.33
    퓰
    0.33
     Nutt
    0.32
    声
    0.32
     здание
    0.32
     Ukrainian
    0.32
    POSITIVE LOGITS
     hardwood
    0.51
     hardwoods
    0.47
     regress
    0.43
    木
    0.42
    totals
    0.41
     swamps
    0.41
     signe
    0.40
     çarp
    0.39
     木
    0.39
     kayu
    0.38
    Activations Density 0.043%

    No Known Activations