© 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. 4953
    Prev
    Next
    INDEX
    Explanations

    code and image filenames

    oai_token-act-pair · gemini-2.0-flash

    g

    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
    ########.
    -0.56
    minaire
    -0.50
     Sin
    -0.50
    KeyId
    -0.49
     MessageBoxIcon
    -0.48
    pulsar
    -0.47
    oldt
    -0.47
    }{*}{
    -0.46
     Stück
    -0.46
    eries
    -0.46
    POSITIVE LOGITS
     background
    1.81
     Background
    1.59
    Background
    1.56
    background
    1.54
     BACKGROUND
    1.50
     achtergrond
    1.36
     backgrounds
    1.31
     Hintergrund
    1.27
    BACKGROUND
    1.26
    背景
    1.23
    Activations Density 0.570%

    No Known Activations