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. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 261617
    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
    dan
    1.23
    currencies
    1.17
    nya
    1.16
     Bane
    1.13
    neighbors
    1.09
    नीचर
    1.08
    م
    1.07
    幫助
    1.06
    ᥣ
    1.05
    옆
    1.04
    POSITIVE LOGITS
    a
    1.32
     dein
    1.21
     retainer
    1.12
    ؤلاء
    1.12
    ত্রী
    1.09
     mais
    1.08
    entes
    1.05
    न
    1.05
     আর্থ
    1.04
    apparent
    1.04
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.