© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10630
    Prev
    Next
    INDEX
    Explanations

    sativa, orders, sad, ica, crystalline, earth, species, framework

    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_13_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
    rashed
    0.52
    했다
    0.49
     infancia
    0.49
    ัก
    0.48
    disconnect
    0.46
    റിന്റെ
    0.46
    梧
    0.46
    saw
    0.45
     wła
    0.45
     llegó
    0.45
    POSITIVE LOGITS
    \
    0.50
     dilemmas
    0.48
    ]
    0.47
    </td>
    0.46
     maximization
    0.45
     overcoming
    0.45
    Who
    0.44
    はある
    0.43
    Would
    0.43
     averaging
    0.43
    Activations Density 0.038%

    No Known Activations