© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126090
    Prev
    Next
    INDEX
    Explanations

    entrepreneurial / because / maintain

    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_3_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
    to
    0.95
    such
    0.81
     in
    0.80
     to
    0.80
     at
    0.80
    ک
    0.77
    ای
    0.77
    s
    0.77
    ח
    0.76
    tic
    0.75
    POSITIVE LOGITS
    ные
    0.70
     QLabel
    0.64
     DOI
    0.61
     AAA
    0.61
     Lieut
    0.60
     ItemStack
    0.60
     ImageView
    0.59
     insistent
    0.59
    ü
    0.59
     Mercy
    0.58
    Activations Density 0.012%

    No Known Activations