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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10745
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to organizations and activities for young people

    oai_token-act-pair · gemini-2.0-flash

    community engagement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.77
    期刊论文
    -0.59
     Arquivado
    -0.57
    mybatisplus
    -0.56
     intptr
    -0.55
     døde
    -0.54
     sagde
    -0.52
     PLWABN
    -0.52
    WillAppear
    -0.50
     Himo
    -0.50
    POSITIVE LOGITS
    MLLoader
    0.59
     disambiguazione
    0.49
    EndInit
    0.48
    OLOGIE
    0.48
    KERN
    0.47
     internetowa
    0.47
    xaml
    0.47
    cabo
    0.46
     acon
    0.46
    principalTable
    0.45
    Activations Density 6.907%

    No Known Activations