© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140808
    Prev
    Next
    INDEX
    Explanations

    countries and historical events

    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
     проведение
    0.55
    rui
    0.50
    cka
    0.50
    тный
    0.50
     ছাদে
    0.50
    孫
    0.50
     ஆனால்
    0.49
     interviewee
    0.49
    cedented
    0.49
    Serbia
    0.49
    POSITIVE LOGITS
     ethers
    0.55
     alert
    0.52
     from
    0.52
    нес
    0.52
    =$
    0.49
     RoHS
    0.49
    Ok
    0.48
     wallets
    0.48
    s
    0.48
     hy
    0.48
    Activations Density 0.002%

    No Known Activations