© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122093
    Prev
    Next
    INDEX
    Explanations

    DCG (Discounted Cumulative Gain)

    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
    t
    0.93
    r
    0.82
     compres
    0.82
    ture
    0.81
    tura
    0.79
    treatment
    0.78
    ्स
    0.78
    at
    0.77
    tR
    0.76
    tas
    0.75
    POSITIVE LOGITS
    ق
    0.95
     as
    0.88
    ם
    0.80
     chagrin
    0.79
    د
    0.73
    פ
    0.70
    ف
    0.69
     ප්‍ර
    0.69
     cardiomy
    0.66
    أ
    0.66
    Activations Density 0.002%

    No Known Activations