© 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. 5368
    Prev
    Next
    INDEX
    Explanations

    includes listing items or rules

    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
    ส์
    1.51
    𝑠
    1.49
     gou
    1.48
    jak
    1.48
    JAK
    1.46
     sump
    1.36
    zial
    1.35
     nargs
    1.30
     dozen
    1.26
     Mostly
    1.26
    POSITIVE LOGITS
    ма
    1.55
    अप
    1.47
    бат
    1.44
    経過
    1.44
     сам
    1.43
    咙
    1.41
    
    1.38
     vess
    1.36
    嚨
    1.36
    પણે
    1.35
    Activations Density 0.016%

    No Known Activations