© 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. 10014
    Prev
    Next
    INDEX
    Explanations

    terms or phrases related to legal or bureaucratic governance

    oai_token-act-pair · gemini-2.0-flash

    force

    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
    IVEREF
    -0.73
    tvguidetime
    -0.68
    InputBorder
    -0.64
     كومونز
    -0.64
    HtmlAttribute
    -0.64
    :✨
    -0.61
    NUMX
    -0.61
    ̍
    -0.61
     kosher
    -0.60
     Numerade
    -0.60
    POSITIVE LOGITS
    urysty
    0.50
    pejo
    0.49
    getSystemService
    0.47
    <bos>
    0.46
     Администра
    0.45
    ApiProperty
    0.45
    muebles
    0.45
     situe
    0.44
    Suma
    0.44
    sillos
    0.44
    Activations Density 6.360%

    No Known Activations