© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 1749
    Prev
    Next
    INDEX
    Explanations

    have/has

    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_44_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
    ..<
    0.44
    люб
    0.42
    люби
    0.38
    ...+
    0.37
     koh
    0.35
     ۔۔
    0.35
    ziert
    0.35
    杜
    0.35
    extractor
    0.34
     てる
    0.34
    POSITIVE LOGITS
     имеет
    0.78
     имеют
    0.71
     має
    0.68
     punya
    0.67
     tiene
    0.66
     memiliki
    0.65
     tenía
    0.64
     име
    0.60
     mempunyai
    0.59
     мають
    0.59
    Activations Density 0.520%

    No Known Activations