© 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. 8958
    Prev
    Next
    INDEX
    Explanations

    words within text related to labor, work, and manual effort

    oai_token-act-pair · gemini-2.0-flash

    action verbs related to manual labor

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

    land and farming

    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
    tagHelperRunner
    -0.50
    :"-"`
    -0.47
    EndGlobalSection
    -0.43
    chevron
    -0.39
    opedia
    -0.39
    hofen
    -0.39
    من
    -0.37
     PackageManager
    -0.37
     ngan
    -0.36
     delegation
    -0.36
    POSITIVE LOGITS
    AxisAlignment
    0.75
     utafitiHapana
    0.69
    audiovisuel
    0.68
     lay
    0.68
     mow
    0.66
     sweep
    0.65
     till
    0.65
    PreferredItem
    0.64
     ProtoMessage
    0.64
     laid
    0.63
    Activations Density 2.052%

    No Known Activations