© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2519
    Prev
    Next
    INDEX
    Explanations

    sentences discussing when something began or was founded, often using the words "start," "first," or "originally".

    oai_token-act-pair · gemini-2.0-flash

    origin

    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
    +#+
    -0.77
    VersionUID
    -0.67
    complexType
    -0.66
    rinfo
    -0.63
    complexContent
    -0.61
     nakalista
    -0.60
    StoryboardSegue
    -0.59
     AssemblyCulture
    -0.59
     Signalez
    -0.58
    TestingModule
    -0.58
    POSITIVE LOGITS
    <bos>
    1.20
    Original
    0.62
    Originally
    0.61
     original
    0.59
    GEBURTSDATUM
    0.58
     Originally
    0.57
     ursprüng
    0.56
     originally
    0.56
    начала
    0.55
    original
    0.54
    Activations Density 2.201%

    No Known Activations