© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13170
    Prev
    Next
    INDEX
    Explanations

    instructions, specifically those involving putting images in boxes

    oai_token-act-pair · gemini-2.0-flash

    box

    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
    Not in Any Lists

    No Comments

    Negative Logits
     AttributeSet
    -0.69
    رشف
    -0.65
     EconPapers
    -0.62
     متعلقه
    -0.58
    bcryptjs
    -0.52
    DoubleQuotes
    -0.50
     colspan
    -0.49
    enumi
    -0.49
    }{*}{
    -0.49
    BindingResult
    -0.49
    POSITIVE LOGITS
     resourceCulture
    0.66
    曖昧さ回避
    0.66
    Wpf
    0.54
    <bos>
    0.51
    Bronnen
    0.49
     bö
    0.48
    ///</
    0.48
    LookAnd
    0.48
    States
    0.48
    Wechat
    0.48
    Activations Density 0.439%

    No Known Activations