© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 77776
    Prev
    Next
    INDEX
    Explanations

    method definition or assignment

    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_29_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
     reversion
    0.44
     convinc
    0.44
     messaggio
    0.43
     संदेश
    0.41
    फाइन
    0.40
     convain
    0.40
    ﯼ
    0.40
    🔈
    0.39
     پیغام
    0.39
     mensajes
    0.39
    POSITIVE LOGITS
     billionaires
    0.42
    phal
    0.41
     billionaire
    0.39
     подру
    0.39
     heterogeneous
    0.39
    zhen
    0.39
    kova
    0.38
    tors
    0.38
    rez
    0.37
     tropical
    0.37
    Activations Density 0.002%

    No Known Activations