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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 244628
    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_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
    ిన
    1.23
    E
    1.17
    O
    1.14
     Бога
    1.04
    法
    1.04
    stands
    1.02
    hin
    1.01
     IQ
    1.01
    S
    1.01
    //
    0.99
    POSITIVE LOGITS
     apresentação
    1.41
     retourner
    1.36
     versão
    1.34
     richt
    1.27
     cadeau
    1.25
     하지만
    1.24
     réparation
    1.22
     grâce
    1.21
    bouncer
    1.21
    ၤ
    1.20
    Activations Density 0.000%

    No Known Activations