© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11435
    Prev
    Next
    INDEX
    Explanations

    technology terms, especially social media, and also some names

    oai_token-act-pair · gemini-2.0-flash

    social media platforms

    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
    存于互联网档案馆
    -0.54
    omitempty
    -0.50
    Einzelnachweise
    -0.50
    TikTok
    -0.48
    ToBounds
    -0.46
     getItemCount
    -0.45
    PostExecute
    -0.45
    wyneth
    -0.45
     kvad
    -0.43
    Παραπομπές
    -0.42
    POSITIVE LOGITS
    ADELPHIA
    0.62
    Datuak
    0.62
    ászló
    0.57
     solicitation
    0.57
    Filmografie
    0.56
    iettivo
    0.56
    TagMode
    0.56
    <bos>
    0.56
    Personensuche
    0.55
    utilisons
    0.54
    Activations Density 6.886%

    No Known Activations