© 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. 136411
    Prev
    Next
    INDEX
    Explanations

    Italian Prime Ministers or government figures

    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
    幸运
    0.47
     tồn
    0.47
    วัน
    0.46
    这里
    0.46
    羟
    0.46
     Koreans
    0.45
    </sup>
    0.45
    бла
    0.45
    Fond
    0.45
    瓶
    0.44
    POSITIVE LOGITS
    effects
    0.48
    elo
    0.48
     ي
    0.48
    ми
    0.47
    ка
    0.47
    zentration
    0.47
    aping
    0.47
    عت
    0.47
    きました
    0.47
    effet
    0.46
    Activations Density 0.000%

    No Known Activations