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. 244517
    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
     percor
    1.18
    '.
    1.09
    Objet
    1.09
    '-
    1.07
    まず
    1.06
    ivy
    1.05
     cỡ
    1.05
     limpiar
    1.04
    fork
    1.04
     براہ
    1.04
    POSITIVE LOGITS
    มั่น
    1.27
    نا
    1.23
     brink
    1.13
     scheming
    1.11
    เสริม
    1.10
    ंदोल
    1.09
    ня
    1.06
    lifting
    1.06
     insulting
    1.05
    ऍ
    1.04
    Activations Density 0.000%

    No Known Activations