© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4797
    Prev
    Next
    INDEX
    Explanations

    technical writing, identifying common words and phrases used when defining processes, materials, and experimental setups.

    oai_token-act-pair · gemini-2.0-flash

    use

    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
    ensä
    -0.46
     hasattr
    -0.45
     getMax
    -0.44
     gestern
    -0.44
     expect
    -0.44
     benefit
    -0.43
     vielä
    -0.43
    以上就是
    -0.43
    apos
    -0.42
    Berikut
    -0.42
    POSITIVE LOGITS
     CreateTagHelper
    0.76
    uxxxx
    0.76
     AssemblyCulture
    0.75
    UnusedPrivate
    0.75
    CloseOperation
    0.72
     الاطلاع
    0.70
     المعيارى
    0.69
    ReusableCell
    0.69
     <<<<<<<<<<<<<<
    0.68
    IntoConstraints
    0.66
    Activations Density 2.673%

    No Known Activations