© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83088
    Prev
    Next
    INDEX
    Explanations

    Spanish, Hindi, Japanese, Russian, Arabic, Turkish, culture, rent

    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_0_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
     belieb
    1.30
    يد
    1.28
    ak
    1.24
    يه
    1.24
    బర్
    1.19
    ovány
    1.15
    家
    1.14
    َات
    1.13
    ↵↵
    1.12
    ova
    1.10
    POSITIVE LOGITS
    0
    1.66
    ۔
    1.47
    \
    1.46
    ва
    1.42
     подклю
    1.41
    s
    1.41
    ي
    1.41
    sı
    1.41
     reasoned
    1.39
    し
    1.39
    Activations Density 0.000%

    No Known Activations