© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12528
    Prev
    Next
    INDEX
    Explanations

    words and phrases that appear to link multiple concepts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     «
    -0.60
    webElement
    -0.54
    <eos>
    -0.52
     مح
    -0.47
     and
    -0.46
    ssaint
    -0.46
    Viki
    -0.44
     argument
    -0.44
     po
    -0.44
    <strong>
    -0.44
    POSITIVE LOGITS
    tvguidetime
    1.14
     Efq
    0.91
    出版年
    0.90
    AnimationsModule
    0.82
     Houſe
    0.75
     Jefus
    0.75
    "?>
    0.73
     themſelves
    0.72
    TypedDataSet
    0.71
     NSCoder
    0.71
    Activations Density 17.810%

    No Known Activations