© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23546
    Prev
    Next
    INDEX
    Explanations

    "Particular"

    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_56_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
     troubled
    0.89
     Distress
    0.75
     distressed
    0.75
     troubles
    0.73
    烦
    0.72
     distress
    0.71
    でお
    0.68
    trou
    0.66
    Trou
    0.66
     Trou
    0.64
    POSITIVE LOGITS
    Particular
    0.43
     Particular
    0.41
    Ꮅ
    0.39
     particuliers
    0.38
     particulier
    0.38
     Surprise
    0.38
     터
    0.37
     частности
    0.37
     ধারাবাহ
    0.36
     перио
    0.36
    Activations Density 0.023%

    No Known Activations