© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5037
    Prev
    Next
    INDEX
    Explanations

    words related to Facebook, mobile phones, and a general account process

    oai_token-act-pair · gemini-2.0-flash

    technical identifiers specific to Facebook

    np_token-act-pair-logits · gpt-4o-mini

    Facebook and other languages

    np_max-act-logits · gemini-2.0-flash
    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
    — 
    -0.66
    BagLayout
    -0.65
     imageNamed
    -0.62
    出版年
    -0.62
    :].
    -0.57
    はじめに
    -0.55
    BufferException
    -0.54
    uminum
    -0.52
    mushroom
    -0.52
    AndEndTag
    -0.52
    POSITIVE LOGITS
     propOrder
    0.60
    u
    0.58
    !*\
    0.55
    τος
    0.54
     Diſ
    0.54
    ů
    0.52
    SerializedSize
    0.49
    ului
    0.48
    AsUp
    0.48
    града
    0.48
    Activations Density 1.126%

    No Known Activations