© 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. 1559
    Prev
    Next
    INDEX
    Explanations

    computer code and radio communications terminology

    oai_token-act-pair · gemini-2.0-flash

    OTH

    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
    ArgsConstructor
    -0.82
    clerview
    -0.78
     typelib
    -0.73
    Beijinhos
    -0.73
    ulipas
    -0.70
    mybatisplus
    -0.69
    WriteTagHelper
    -0.69
     LIABLE
    -0.65
    COUVER
    -0.65
     nhàng
    -0.65
    POSITIVE LOGITS
    <bos>
    0.50
    inheritdoc
    0.46
    CreateModel
    0.45
    pagination
    0.44
    as
    0.44
    radio
    0.44
     vym
    0.42
    drá
    0.40
    无线
    0.40
     radio
    0.40
    Activations Density 0.896%

    No Known Activations