Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 261302
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
     belong
    1.13
     channeling
    1.04
    ્યાર
    1.01
     larga
    1.00
     icing
    0.99
     suyo
    0.98
     satisfy
    0.98
    ′
    0.98
     constitut
    0.97
    έ
    0.97
    POSITIVE LOGITS
    editar
    1.49
    ls
    1.31
    क्ती
    1.30
     фараз
    1.22
    ायचे
    1.22
    калә
    1.21
    ाय
    1.18
    ❻
    1.17
    迢
    1.17
     देशा
    1.17
    Activations Density 0.000%

    No Known Activations