© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12308
    Prev
    Next
    INDEX
    Explanations

    text discussing boycotting and intention to visit particular US states

    oai_token-act-pair · gemini-2.0-flash

    co

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    TagMode
    -0.65
    جغرافيا
    -0.64
    GEBURTSDATUM
    -0.61
     typelib
    -0.61
    IVEREF
    -0.56
    BeginContext
    -0.52
    EDEFAULT
    -0.52
     hObject
    -0.52
    MessageTagHelper
    -0.50
    inov
    -0.49
    POSITIVE LOGITS
    MLLoader
    0.63
    udnio
    0.56
     referrerpolicy
    0.54
    Попис
    0.50
    Carriera
    0.48
    GRANTED
    0.48
    Demografia
    0.47
    <%@
    0.46
    '])->
    0.46
     &___
    0.46
    Activations Density 1.085%

    No Known Activations