© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139165
    Prev
    Next
    INDEX
    Explanations

    economic services and market failures

    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_12_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
     دہ
    0.49
     chooser
    0.49
     उसमें
    0.47
    quy
    0.46
    함
    0.46
    उस
    0.46
    ıştır
    0.45
     تعیین
    0.45
    ちは
    0.44
     አስተ
    0.44
    POSITIVE LOGITS
    AL
    0.55
    EL
    0.54
    KINS
    0.53
    ALA
    0.52
    el
    0.48
     Galle
    0.47
    EN
    0.46
    </li>
    0.46
     Excessive
    0.45
     Hacienda
    0.44
    Activations Density 0.014%

    No Known Activations