© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3189
    Prev
    Next
    INDEX
    Explanations

    parts of email messages, including headers and URLs

    oai_token-act-pair · gemini-2.0-flash

    Internet forum posts

    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
     AssemblyProduct
    -0.54
    enumii
    -0.50
     wzi
    -0.47
    fromnode
    -0.47
    CAPTURE
    -0.45
    angliski
    -0.45
    nip
    -0.44
    igte
    -0.43
    Captured
    -0.43
     reconoc
    -0.42
    POSITIVE LOGITS
     ddelweddau
    0.68
    zeß
    0.66
     otomatig
    0.63
    blos
    0.63
    saraba
    0.61
     EconPapers
    0.59
    下载附件
    0.59
    IsMutable
    0.57
    }}^{(
    0.57
    }}{(
    0.57
    Activations Density 1.527%

    No Known Activations