© 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. 10898
    Prev
    Next
    INDEX
    Explanations

    phrases that quantify or describe the extent of something

    oai_token-act-pair · gemini-2.0-flash

    of

    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
    someone
    -1.06
     something
    -1.05
    Somebody
    -1.05
    Someone
    -1.04
     Somebody
    -1.03
    somebody
    -1.02
     somebody
    -1.02
     Someone
    -1.00
     someone
    -0.99
    something
    -0.95
    POSITIVE LOGITS
    braith
    0.47
     mixed
    0.47
     mo
    0.47
    <bos>
    0.45
    mixed
    0.43
    Box
    0.43
    iants
    0.42
    ான
    0.41
     thee
    0.41
     Dahl
    0.41
    Activations Density 2.561%

    No Known Activations