© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12727
    Prev
    Next
    INDEX
    Explanations

    URL-like structures

    oai_token-act-pair · gemini-2.0-flash

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     /
    -0.66
    /
    -0.65
    <bos>
    -0.65
    )/
    -0.65
     $/
    -0.57
    ))/
    -0.57
    /"
    -0.54
    /-
    -0.52
    >/
    -0.52
    /'
    -0.51
    POSITIVE LOGITS
     المعيارى
    0.92
    AndEndTag
    0.82
    richTextPanel
    0.79
     defStyleAttr
    0.79
    enumi
    0.77
     Houſe
    0.77
     Chriſt
    0.76
     Macromolecules
    0.75
     ſeveral
    0.74
     zircon
    0.73
    Activations Density 0.983%

    No Known Activations