© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130695
    Prev
    Next
    INDEX
    Explanations

    Chinese, Russian, English words

    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_6_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
    ight
    1.13
    ní
    1.05
    deling
    1.02
    ton
    0.99
    elling
    0.96
    tingham
    0.93
    ním
    0.92
    -|
    0.91
     sehen
    0.89
     सेल्फी
    0.89
    POSITIVE LOGITS
    ↵↵
    1.51
    지
    1.31
    ع
    1.20
    ش
    1.08
    จะ
    1.01
    ی
    0.99
    ї
    0.98
    י
    0.97
    기
    0.97
    ای
    0.96
    Activations Density 0.000%

    No Known Activations