© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97407
    Prev
    Next
    INDEX
    Explanations

    lungs

    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_14_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
    {
    0.49
    気に
    0.47
    शे
    0.46
    完全に
    0.46
    ছে
    0.45
    do
    0.44
    dep
    0.43
    June
    0.43
    മ്
    0.43
    今日は
    0.42
    POSITIVE LOGITS
     elution
    0.59
     seaweed
    0.58
     attenuation
    0.57
     myocardium
    0.56
     glial
    0.54
     AGN
    0.53
     ง
    0.53
     analges
    0.53
    女兒
    0.53
     endogenous
    0.52
    Activations Density 0.000%

    No Known Activations