© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 235029
    Prev
    Next
    INDEX
    Explanations

    motion and displacement

    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_32_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
     shrine
    0.36
     FID
    0.35
    不是
    0.35
     ANS
    0.34
    窅
    0.34
    agog
    0.34
    火
    0.34
    墓
    0.34
    Editing
    0.33
     saddle
    0.33
    POSITIVE LOGITS
    yaf
    0.39
     Organization
    0.37
     jau
    0.36
    صاف
    0.35
    tras
    0.34
     displacements
    0.34
    bewegung
    0.34
    mono
    0.34
     ടി
    0.34
    сера
    0.34
    Activations Density 0.027%

    No Known Activations