© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4737
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to naming, describing, and defining terms

    oai_token-act-pair · gemini-2.0-flash

    Language terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ,:),
    -0.76
     nameof
    -0.72
     siè
    -0.66
    NOPQRST
    -0.65
    impulan
    -0.63
    xit
    -0.61
    )");
    -0.61
    `,
    -0.60
    tú
    -0.60
    FieldBuilder
    -0.60
    POSITIVE LOGITS
     fă
    0.56
    ValueStyle
    0.47
     ordem
    0.46
    stateParams
    0.45
    ásra
    0.43
    —
    0.41
    Clik
    0.38
    ValueGenerated
    0.38
     means
    0.37
    行者
    0.37
    Activations Density 5.348%

    No Known Activations