© 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. 7373
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to research study design, methodology, and rationale

    oai_token-act-pair · gemini-2.0-flash

    prepositions and conjunctions

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

    Reasons and explanations

    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
    aarrggbb
    -1.05
     '\\;'
    -0.79
    RTEE
    -0.71
    oredCriteria
    -0.70
    jspx
    -0.69
    StackNavigator
    -0.69
    Portale
    -0.68
    featureID
    -0.68
    AntiForgeryToken
    -0.67
    脚注の使い方
    -0.66
    POSITIVE LOGITS
     for
    2.66
    for
    1.79
     для
    1.64
     untuk
    1.55
     voor
    1.54
     für
    1.53
     pentru
    1.38
     برای
    1.35
     för
    1.27
    สำหรับ
    1.27
    Activations Density 5.717%

    No Known Activations