© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3508
    Prev
    Next
    INDEX
    Explanations

    throw at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
     spoken
    1.33
     lease
    1.33
     livelihood
    1.29
    
    1.20
     
    1.18
     Capsule
    1.13
     apothe
    1.10
     criteria
    1.09
    ווה
    1.09
     diction
    1.08
    POSITIVE LOGITS
    ి
    1.55
    י
    1.45
    ي
    1.44
    ি
    1.39
    ी
    1.31
    ardier
    1.27
    يّ
    1.24
    عت
    1.22
    ून
    1.18
    РА
    1.18
    Activations Density 0.043%

    No Known Activations