© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 351
    Prev
    Next
    INDEX
    Explanations

    3D modeling and rendering concepts

    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
    年モデル
    0.27
    車種
    0.26
    州市
    0.25
    awr
    0.25
    züge
    0.25
     पार्किंग
    0.24
    adobe
    0.24
    绦
    0.24
    эф
    0.24
     xhr
    0.24
    POSITIVE LOGITS
    unate
    0.35
     Bones
    0.35
     bones
    0.32
    smo
    0.31
     pyramid
    0.31
     pyramids
    0.30
     Pyramid
    0.30
     smoothed
    0.29
     Kingdoms
    0.29
     subdivision
    0.28
    Activations Density 0.041%

    No Known Activations