© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201621
    Prev
    Next
    INDEX
    Explanations

    healthy person/man

    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_12_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
     healthy
    0.56
    mai
    0.56
    ré
    0.55
    лау
    0.54
    的
    0.54
     Healthy
    0.54
    b
    0.54
    ding
    0.52
    y
    0.51
    dise
    0.50
    POSITIVE LOGITS
     Emperor
    0.57
    皇帝
    0.57
    unnel
    0.53
    მწიფ
    0.52
     jednotliv
    0.52
     მნიშვნელ
    0.52
     veniva
    0.52
     unzip
    0.51
     interrogate
    0.51
     tunnel
    0.50
    Activations Density 0.001%

    No Known Activations