© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215883
    Prev
    Next
    INDEX
    Explanations

    motion

    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_50_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
     이전
    1.08
    移
    0.94
     przen
    0.89
     옮
    0.80
     пере
    0.76
     الانتق
    0.76
     relocation
    0.73
    옮
    0.73
     přes
    0.73
     перено
    0.71
    POSITIVE LOGITS
    动
    0.52
    動
    0.45
    动的
    0.44
     MOTION
    0.44
     Beweg
    0.42
    動作
    0.41
    动作
    0.41
    動き
    0.41
     തു
    0.41
     Motion
    0.40
    Activations Density 0.006%

    No Known Activations