© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3745
    Prev
    Next
    INDEX
    Explanations

    references to geography and local scenes

    oai_token-act-pair · gemini-2.0-flash

    local area

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    AdapterView
    -0.52
    แต่ง
    -0.47
     war
    -0.46
    HSSF
    -0.45
     War
    -0.45
    ropractic
    -0.44
     "
    -0.44
    war
    -0.44
    īg
    -0.44
     try
    -0.43
    POSITIVE LOGITS
    NameInMap
    0.90
    <bos>
    0.90
    TagHelper
    0.88
    Autoritní
    0.81
     AssemblyCompany
    0.80
    tagHelperRunner
    0.77
    脚注の使い方
    0.77
    Aiheesta
    0.75
    BeginContext
    0.75
    #+#
    0.72
    Activations Density 1.948%

    No Known Activations