© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61248
    Prev
    Next
    INDEX
    Explanations

    a reflection of something

    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_11_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
    \
    0.81
    </a>
    0.69
    </strong>
    0.67
     Functions
    0.67
    <0xE3>
    0.66
    $
    0.61
    )
    0.60
     Sebastián
    0.60
       
    0.59
    \]
    0.59
    POSITIVE LOGITS
     equipamento
    0.64
     rammed
    0.63
    chand
    0.63
    fireFlower
    0.59
    chore
    0.59
     оборудование
    0.59
     jind
    0.59
     extinguished
    0.58
     loung
    0.57
    κτή
    0.57
    Activations Density 0.003%

    No Known Activations