© 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. 10885
    Prev
    Next
    INDEX
    Explanations

    the phrase "press conference"

    oai_token-act-pair · gemini-2.0-flash

    conference

    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
    BeginContext
    -1.06
    unknownFields
    -0.81
    %</
    -0.79
    Πηγή
    -0.79
    })();
    -0.77
    ITERATURE
    -0.75
    ERATION
    -0.73
    )}</
    -0.73
    انتهای
    -0.73
    FormTagHelper
    -0.72
    POSITIVE LOGITS
    ない
    0.55
     original
    0.52
     pour
    0.52
     Emp
    0.52
     ha
    0.52
    、
    0.51
    平
    0.51
    多
    0.50
     est
    0.50
     and
    0.50
    Activations Density 0.138%

    No Known Activations