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. 261531
    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
    ্ধ্য
    1.25
    логии
    1.24
    nnnn
    1.23
    thet
    1.22
     يص
    1.17
    תו
    1.16
    musik
    1.16
    과
    1.16
    ²,
    1.14
     scrittura
    1.14
    POSITIVE LOGITS
    া
    1.12
     intima
    1.07
     afford
    1.06
     underlie
    1.03
     ogranic
    1.02
     elect
    1.01
    ்ச
    1.01
    ät
    1.00
     деп
    1.00
    atiable
    0.99
    Activations Density 0.000%

    No Known Activations