© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3234
    Prev
    Next
    INDEX
    Explanations

    a variety of number-related words, including those used to label things

    oai_token-act-pair · gemini-2.0-flash

    Legal and social issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    DockStyle
    -0.65
    ızlık
    -0.51
    {#
    -0.48
    Extrait
    -0.48
     nasional
    -0.47
     color
    -0.46
    vací
    -0.46
     puto
    -0.45
    脚注の使い方
    -0.44
    io
    -0.44
    POSITIVE LOGITS
    зулта
    0.68
     EconPapers
    0.66
     Autorisations
    0.66
     GenerationType
    0.63
     IBRARY
    0.62
     незавершена
    0.60
    thâu
    0.60
    ITERIA
    0.59
     HasFactory
    0.57
    imų
    0.57
    Activations Density 12.791%

    No Known Activations