© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143567
    Prev
    Next
    INDEX
    Explanations

    superlatives and large things

    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_46_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    JZ
    0.52
    VJ
    0.46
    JF
    0.41
    JP
    0.41
    Ј
    0.40
    AC
    0.39
     Кали
    0.39
    Calories
    0.39
    JC
    0.38
     JB
    0.38
    POSITIVE LOGITS
     adata
    0.42
    岖
    0.41
     Ле
    0.39
     Sym
    0.39
     Le
    0.39
     Pat
    0.38
     Leuk
    0.38
    iladi
    0.38
     leuc
    0.38
     Sim
    0.38
    Activations Density 0.037%

    No Known Activations