© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9799
    Prev
    Next
    INDEX
    Explanations

    words related to news publishing, computer programming, baseball, and political speaking

    oai_token-act-pair · gemini-2.0-flash

    production

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     
    -0.51
     started
    -0.50
    ./
    -0.47
     began
    -0.47
    ich
    -0.45
    [[
    -0.44
     begun
    -0.43
    تور
    -0.43
     eget
    -0.41
     (
    -0.40
    POSITIVE LOGITS
     myſelf
    1.24
     estekak
    1.08
    +#+#
    1.07
     ſtate
    1.07
    DockStyle
    1.07
     Efq
    1.02
     itſelf
    1.02
     Majefty
    1.00
    ſelf
    0.99
     raiſ
    0.98
    Activations Density 30.064%

    No Known Activations