© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11221
    Prev
    Next
    INDEX
    Explanations

    words related to negative emotions, conflict, disagreement and strong reactions in comments and opinions.

    oai_token-act-pair · gemini-2.0-flash

    Confrontation

    np_max-act · gemini-2.0-flash

    say "of and"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     those
    -0.56
     great
    -0.53
     the
    -0.49
     other
    -0.48
     still
    -0.47
     their
    -0.46
     good
    -0.46
    tude
    -0.46
     doing
    -0.46
     bons
    -0.45
    POSITIVE LOGITS
    GEBURTSDATUM
    1.34
     مرئيه
    0.89
     &___
    0.85
    RegressionTest
    0.82
     AssemblyProduct
    0.82
    DockStyle
    0.81
    IndentedString
    0.81
     CreateTagHelper
    0.79
     AspNetCore
    0.77
     UnityEditor
    0.75
    Activations Density 1.594%

    No Known Activations