© 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. 752
    Prev
    Next
    INDEX
    Explanations

    LaTeX equations

    oai_token-act-pair · gemini-2.0-flash

    Brackets/braces

    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
    inephrine
    -0.45
    OGND
    -0.45
    feinander
    -0.43
     utafitiHapana
    -0.42
     FetchType
    -0.41
     Cæsar
    -0.39
    Viited
    -0.38
    ‍♂️
    -0.38
    APPY
    -0.37
     Sturgeon
    -0.37
    POSITIVE LOGITS
     esternos
    0.69
    tagHelperRunner
    0.60
    ✨:
    0.60
    /*
    0.59
     الرياضيه
    0.57
     MAYO
    0.57
     Chwiliwch
    0.56
     }</
    0.56
    Portail
    0.56
    karan
    0.56
    Activations Density 12.432%

    No Known Activations