© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1867
    Prev
    Next
    INDEX
    Explanations

    code snippets with formatting or tab characters

    oai_token-act-pair · gemini-2.0-flash

    code formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Muñoz
    -0.62
     userRepository
    -0.59
     Sanz
    -0.58
    amazonaws
    -0.57
    redients
    -0.57
    atalyst
    -0.57
     getNombre
    -0.55
    etwork
    -0.55
    gogo
    -0.55
    iber
    -0.55
    POSITIVE LOGITS
    InjectAttribute
    0.81
    peq
    0.74
    ViewFeatures
    0.69
    SerializedSize
    0.68
    帖最后由
    0.68
     Olimpia
    0.66
     مرئيه
    0.65
    +#+
    0.63
     AssemblyProduct
    0.63
    StructEnd
    0.62
    Activations Density 3.840%

    No Known Activations