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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5946
    Prev
    Next
    INDEX
    Explanations

    manager, management, assistant

    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
    a
    1.65
    er
    1.48
    нодоро
    1.44
    on
    1.37
    া
    1.36
    weds
    1.31
    im
    1.26
     ै
    1.25
     trotzdem
    1.21
    
    1.19
    POSITIVE LOGITS
    𝑰
    1.65
    ो
    1.58
    𝒆
    1.55
     partidas
    1.52
    د
    1.50
    𝒖
    1.48
    こと
    1.48
    𝒊
    1.47
    ल
    1.44
    ことにより
    1.43
    Activations Density 0.124%

    No Known Activations