© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12669
    Prev
    Next
    INDEX
    Explanations

    the word "youth" and other words relating to head, hunting, or proving

    oai_token-act-pair · gemini-2.0-flash

    youth

    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
     enfans
    -0.74
     individus
    -0.66
    er
    -0.61
     chré
    -0.60
     épaules
    -0.58
     their
    -0.56
     avoient
    -0.56
     étoient
    -0.55
     the
    -0.54
     suéter
    -0.54
    POSITIVE LOGITS
    RegressionTest
    0.88
     bezeichneter
    0.84
     metastases
    0.83
    fillType
    0.82
    TagMode
    0.79
    >--}}
    0.79
    存于互联网档案馆
    0.77
     Telex
    0.77
     Sensei
    0.75
    WEBPACK
    0.75
    Activations Density 2.038%

    No Known Activations