© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7075
    Prev
    Next
    INDEX
    Explanations

    a mix of terms related to code, anger, and some other concepts

    oai_token-act-pair · gemini-2.0-flash

    alive

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    <bos>
    -0.67
    ↵↵
    -0.43
     
    -0.43
    <eos>
    -0.42
    聘
    -0.39
     spot
    -0.38
    我
    -0.36
    等
    -0.36
    .
    -0.36
    点
    -0.35
    POSITIVE LOGITS
     ModelExpression
    1.15
    webElementXpaths
    1.10
    GEBURTSDATUM
    1.09
     CreateTagHelper
    1.07
     resourceCulture
    1.02
    تقاوى
    1.01
    fjspx
    1.01
     nahilalakip
    0.99
     himo
    0.99
     يتيمه
    0.99
    Activations Density 3.400%

    No Known Activations