© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158867
    Prev
    Next
    INDEX
    Explanations

    intercontinental or transcontinental

    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_2_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
    ED
    1.80
    ك
    1.55
    c
    1.34
    kę
    1.29
    :
    1.29
    ką
    1.25
    س
    1.20
    ق
    1.20
    k
    1.16
    ES
    1.13
    POSITIVE LOGITS
    ли
    1.05
    will
    1.00
     de
    0.99
    łoży
    0.99
    થી
    0.98
    www
    0.97
    տն
    0.96
    to
    0.95
    issez
    0.93
    ੀ
    0.93
    Activations Density 0.000%

    No Known Activations