© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132444
    Prev
    Next
    INDEX
    Explanations

    weekend getaway

    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_1_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
    ר
    1.29
    says
    1.06
    פר
    1.04
    t
    1.03
    to
    1.02
    י
    1.01
    ז
    0.99
    on
    0.98
    廛
    0.96
    tries
    0.95
    POSITIVE LOGITS
     \
    1.63
     are
    1.62
    ية
    1.50
    ة
    1.45
     be
    1.22
    !
    1.21
    :
    1.20
     joka
    1.16
    ك
    1.15
     but
    1.13
    Activations Density 0.000%

    No Known Activations