© 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. 3482
    Prev
    Next
    INDEX
    Explanations

    database schema

    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
    𝗜
    1.66
    
    1.49
    checkFor
    1.48
    ్యూ
    1.46
    operated
    1.46
    원
    1.46
    ANIES
    1.46
     paramInt
    1.45
    foaf
    1.45
     있어
    1.43
    POSITIVE LOGITS
     drown
    1.95
     complic
    1.89
    y
    1.68
    м
    1.67
    tır
    1.64
     cursing
    1.52
     horrified
    1.50
     scav
    1.43
     Maar
    1.43
     lebens
    1.40
    Activations Density 0.002%

    No Known Activations