© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7369
    Prev
    Next
    INDEX
    Explanations

    mentions of ranks and promotions in military and government contexts.

    oai_token-act-pair · gemini-2.0-flash

    forms of the word "name"

    np_token-act-pair-logits · gpt-4o-mini

    named

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    CloseOperation
    -0.97
     صوتيه
    -0.95
    脚注の使い方
    -0.82
    ArgumentParser
    -0.79
    ArrowToggle
    -0.79
    haikusbot
    -0.79
    homonymie
    -0.77
    mybatisplus
    -0.76
    EndInit
    -0.76
    ArgsConstructor
    -0.75
    POSITIVE LOGITS
     named
    0.75
     naming
    0.67
    named
    0.57
     Named
    0.54
     Ap
    0.54
     nome
    0.54
    Name
    0.52
     Naming
    0.52
     nom
    0.52
    Nom
    0.51
    Activations Density 1.944%

    No Known Activations