© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13393
    Prev
    Next
    INDEX
    Explanations

    the discussion of businesses failing and business concepts being overextended, along with the subject of managing conflicts.

    oai_token-act-pair · gemini-2.0-flash

    thin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     مرئيه
    -0.57
     légales
    -0.55
     dispose
    -0.55
    spiller
    -0.54
    ">*</
    -0.53
     Meetings
    -0.51
     immeasurable
    -0.48
    WARM
    -0.47
     Armas
    -0.47
    Населення
    -0.47
    POSITIVE LOGITS
    ſelves
    0.62
     câte
    0.60
     Theſe
    0.58
     חיצוניים
    0.57
     roulant
    0.56
    WaitGroup
    0.55
    wness
    0.54
     houſe
    0.54
     souple
    0.53
    ChildScrollView
    0.52
    Activations Density 0.948%

    No Known Activations