© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34474
    Prev
    Next
    INDEX
    Explanations

    up to

    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_3_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
    م
    0.75
     suport
    0.73
     supportive
    0.71
     supporto
    0.70
    s
    0.70
     지원
    0.69
     support
    0.68
    supports
    0.68
     mendukung
    0.68
    یم
    0.67
    POSITIVE LOGITS
    是
    0.74
    ي
    0.62
    2
    0.61
     Regeln
    0.61
    ↵
    0.60
    }\
    0.58
    ير
    0.55
    ेंटीना
    0.55
     Böl
    0.54
    َّ
    0.54
    Activations Density 0.011%

    No Known Activations