© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4742
    Prev
    Next
    INDEX
    Explanations

    words written in all-caps, especially those associated with political activism or websites

    oai_token-act-pair · gemini-2.0-flash

    random sentences

    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
     of
    -0.33
     or
    -0.31
     in
    -0.29
     the
    -0.29
     if
    -0.29
     at
    -0.28
     a
    -0.26
     do
    -0.26
     for
    -0.26
     to
    -0.25
    POSITIVE LOGITS
    AddTagHelper
    1.30
     itſelf
    1.30
     ་་
    1.30
     ―――――
    1.27
    awtextra
    1.27
    MigrationBuilder
    1.26
    Datuak
    1.24
     ſind
    1.21
    IsContent
    1.19
    TagMode
    1.17
    Activations Density 7.870%

    No Known Activations