© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4454
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to company / organizational culture

    oai_token-act-pair · gemini-2.0-flash

    culture/climate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     &___
    -0.58
     nonatomic
    -0.54
    DispatchToProps
    -0.54
    jsxFileName
    -0.54
    dotenv
    -0.52
    chito
    -0.52
     незавершена
    -0.51
     essenziale
    -0.51
     tayang
    -0.50
     CURIAM
    -0.50
    POSITIVE LOGITS
     protoimpl
    0.57
     jsPsych
    0.56
    viembre
    0.54
    RenderAtEndOf
    0.53
    modelBuilder
    0.52
    SequentialGroup
    0.50
     <",
    0.50
    zembro
    0.47
    StructEnd
    0.46
     становника
    0.46
    Activations Density 5.257%

    No Known Activations