© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7084
    Prev
    Next
    INDEX
    Explanations

    words associated with programming and data analysis

    oai_token-act-pair · gemini-2.0-flash

    input

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     resourceCulture
    -0.69
    saraba
    -0.62
    Tazama
    -0.59
     baterías
    -0.55
     newBuilder
    -0.54
    adaptiveStyles
    -0.54
    ModelSerializer
    -0.54
    FieldOffset
    -0.52
     AttributeSet
    -0.51
    CppCodeGen
    -0.51
    POSITIVE LOGITS
     input
    0.72
     INPUT
    0.70
    input
    0.69
     Input
    0.65
    INPUT
    0.64
    Input
    0.63
     inputs
    0.62
    BuilderFactory
    0.61
     Inputs
    0.59
    输入
    0.58
    Activations Density 2.854%

    No Known Activations