© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5161
    Prev
    Next
    INDEX
    Explanations

    player and what they do

    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_3_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
    𝖙
    1.33
    on
    1.28
    cklen
    1.24
    ad
    1.21
    𝒈
    1.21
    iendo
    1.20
    س
    1.18
     stature
    1.17
    ルの
    1.15
    ча
    1.13
    POSITIVE LOGITS
    й
    1.73
    в
    1.30
    jší
    1.29
    
    1.28
    ✓
    1.26
     soort
    1.24
    ство
    1.23
     Vật
    1.22
    번호
    1.20
    ckers
    1.20
    Activations Density 0.005%

    No Known Activations