© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5871
    Prev
    Next
    INDEX
    Explanations

    words related to academic work, training, and the passage of time, especially in the context of students.

    oai_token-act-pair · gemini-2.0-flash

    school-related activities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     nahilalakip
    -0.99
    runApp
    -0.89
    AndEndTag
    -0.87
    +:+
    -0.83
    __':
    -0.81
    tagHelperRunner
    -0.81
    Попис
    -0.80
     CURIAM
    -0.78
    脚注の使い方
    -0.77
    __":
    -0.77
    POSITIVE LOGITS
     mid
    0.39
    upakan
    0.38
     turn
    0.36
    po
    0.35
    adple
    0.34
     pop
    0.34
     direct
    0.33
     blown
    0.33
    大人の
    0.33
     due
    0.32
    Activations Density 2.684%

    No Known Activations