© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212509
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_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
    k
    1.29
    ك
    1.19
    kring
    1.13
    clientes
    1.12
    يد
    1.08
    وي
    1.06
    kons
    1.06
     و
    1.05
    kval
    1.03
    d
    1.03
    POSITIVE LOGITS
    ά
    1.27
    >
    1.23
    ’
    1.16
    .
    1.05
    dehyde
    1.05
    ated
    1.02
    ุ
    0.98
     theorem
    0.97
    HA
    0.96
    ance
    0.93
    Activations Density 0.000%

    No Known Activations