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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2376
    Prev
    Next
    INDEX
    Explanations

    angle brackets enclosing something in program code

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Get
    -0.72
     Save
    -0.71
     Find
    -0.69
     Take
    -0.68
     Do
    -0.68
     Add
    -0.65
     Send
    -0.64
     Buy
    -0.64
     Stop
    -0.63
     Pay
    -0.62
    POSITIVE LOGITS
    AndEndTag
    0.86
    tvguidetime
    0.84
     تضيفلها
    0.82
    OGND
    0.81
     autorytatywna
    0.81
    IsContent
    0.80
    出版年
    0.80
    Билгалдахарш
    0.77
    AnchorStyles
    0.74
     wikipagina
    0.73
    Activations Density 9.374%

    No Known Activations