© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126941
    Prev
    Next
    INDEX
    Explanations

    displace / 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_37_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
    Est
    0.40
    Emp
    0.39
    Travel
    0.38
     Est
    0.38
    Serv
    0.38
    賃
    0.37
    旅行
    0.37
     Jade
    0.36
    Commun
    0.36
    顺
    0.36
    POSITIVE LOGITS
     displace
    0.98
     displacement
    0.95
     Displacement
    0.91
     displaced
    0.83
    displacement
    0.81
     displ
    0.81
     displacements
    0.81
     displacing
    0.77
     desplazamiento
    0.65
     desloc
    0.60
    Activations Density 0.001%

    No Known Activations