© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11559
    Prev
    Next
    INDEX
    Explanations

    code snippets and syntax markers

    oai_token-act-pair · gemini-2.0-flash

    programming syntax related to API requests

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ंदीखरीदारी
    -0.64
    Erfolge
    -0.51
     <<<<<<<<<<<<<<
    -0.48
     CreateTagHelper
    -0.46
     /\.
    -0.45
     transfieras
    -0.44
    Bibliograf
    -0.43
     geslacht
    -0.43
    tvguidetime
    -0.43
    Atsauces
    -0.43
    POSITIVE LOGITS
    urlopen
    0.66
    BeginContext
    0.60
    expandindo
    0.58
    orace
    0.58
    ollectionView
    0.58
    AsUp
    0.56
    ğraf
    0.55
    terase
    0.55
     vícti
    0.54
    AutoScaleMode
    0.54
    Activations Density 0.624%

    No Known Activations