© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14061
    Prev
    Next
    INDEX
    Explanations

    dates and/or code snippets or related syntax

    oai_token-act-pair · gemini-2.0-flash

    Code and technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    -0.91
     NSCoder
    -0.83
     дописавши
    -0.69
    يكب
    -0.62
    TypedDataSet
    -0.58
     alimentaria
    -0.58
     htons
    -0.58
     становника
    -0.57
     ***!
    -0.57
    BeginContext
    -0.56
    POSITIVE LOGITS
     e
    0.90
     eh
    0.57
    e
    0.55
    msgTypes
    0.49
    ring
    0.47
     E
    0.47
    TEMPO
    0.46
    ｅ
    0.44
    tinyos
    0.44
    Pautan
    0.42
    Activations Density 2.237%

    No Known Activations