© 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. 2675
    Prev
    Next
    INDEX
    Explanations

    words in personal anecdotes having to do with reflection on a project or experience

    oai_token-act-pair · gemini-2.0-flash

    words related to tasks and assignments

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

    Tasks and exercises

    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
    ModelAdmin
    -0.59
    ViewImports
    -0.59
     recours
    -0.58
    mybatisplus
    -0.57
    省市镇
    -0.54
     ModelExpression
    -0.53
     verwijzen
    -0.52
     slashing
    -0.50
     Paglinawan
    -0.50
    存于互联网档案馆
    -0.48
    POSITIVE LOGITS
     task
    1.57
     tasks
    1.45
     exercises
    1.41
     exercise
    1.39
    task
    1.37
     assignment
    1.37
     assignments
    1.33
     Tasks
    1.29
     Assignment
    1.27
    Exercise
    1.26
    Activations Density 4.388%

    No Known Activations