© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5099
    Prev
    Next
    INDEX
    Explanations

    the word "obtain" and related words

    oai_token-act-pair · gemini-2.0-flash

    obtain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ing
    -0.69
    s
    -0.63
    <strong>
    -0.61
    <eos>
    -0.61
    5
    -0.56
    7
    -0.56
    ↵
    -0.55
     celor
    -0.54
    1
    -0.54
    ity
    -0.54
    POSITIVE LOGITS
    <bos>
    1.68
     propOrder
    1.16
    Autoritní
    1.09
    GEBURTSDATUM
    1.07
     CreateTagHelper
    1.07
     kaarangay
    1.04
     autorytatywna
    1.00
    ⓧ
    0.99
    featureID
    0.98
    verwijspagina
    0.96
    Activations Density 0.961%

    No Known Activations