© 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. 2248
    Prev
    Next
    INDEX
    Explanations

    code snippets, notably Java

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     String
    -1.25
    Math
    -1.20
    String
    -1.20
     Math
    -1.20
     string
    -1.13
    string
    -1.05
    System
    -0.96
     STRING
    -0.94
     System
    -0.93
     Integer
    -0.91
    POSITIVE LOGITS
     متعلقه
    0.80
    ⓧ
    0.71
    EndInit
    0.64
    TagMode
    0.59
     تضيفلها
    0.59
    Personendaten
    0.57
    SharedCtor
    0.56
     ویکی‌پدیا
    0.56
    ImageContext
    0.56
     noqa
    0.55
    Activations Density 1.252%

    No Known Activations