© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3498
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to debate and deliberation

    oai_token-act-pair · gemini-2.0-flash

    discussion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     discussion
    -2.16
     discussions
    -1.81
     discuss
    -1.80
    discussion
    -1.77
     discussing
    -1.77
     discussed
    -1.74
     Discussions
    -1.71
     Discussion
    -1.69
    Discussion
    -1.63
    discuss
    -1.61
    POSITIVE LOGITS
    adaptiveStyles
    0.87
     MainAxisSize
    0.85
     linkovi
    0.70
    󠁢
    0.69
    DebuggerNonUser
    0.69
    RenderAtEndOf
    0.68
    )";
    0.68
    TagHelper
    0.67
    ScopeManager
    0.66
     Suivez
    0.66
    Activations Density 7.327%

    No Known Activations