© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7106
    Prev
    Next
    INDEX
    Explanations

    a variety of terms, especially those that may be keywords or of particular importance in legal or technical contexts, along with some terms related to communication and a number

    oai_token-act-pair · gemini-2.0-flash

    email and links

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    تقاوى
    -0.98
    +#+#
    -0.93
    webElementXpaths
    -0.90
    expandindo
    -0.86
     raiſ
    -0.84
     purpoſe
    -0.84
     Cæsar
    -0.83
     Bioaccumulative
    -0.82
     Majefty
    -0.81
     EconPapers
    -0.80
    POSITIVE LOGITS
    рог
    0.59
     (
    0.54
     is
    0.53
    iência
    0.50
     are
    0.50
    ting
    0.50
     presented
    0.48
    ย์
    0.47
    ter
    0.45
    vara
    0.45
    Activations Density 6.559%

    No Known Activations