© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4201
    Prev
    Next
    INDEX
    Explanations

    mentions of spending time, consideration, and related concepts of leisure and engagement.

    oai_token-act-pair · gemini-2.0-flash

    time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    цездатний
    -0.67
    MigrationBuilder
    -0.55
    principalTable
    -0.54
    llung
    -0.51
    +#+#
    -0.50
    Aggreg
    -0.49
    ElementException
    -0.48
     дописавши
    -0.48
     besök
    -0.48
    Identyfik
    -0.48
    POSITIVE LOGITS
    WriteTagHelper
    0.75
    
    0.63
     PopupWindow
    0.60
     muualla
    0.59
    addPreferredGap
    0.57
     to
    0.53
     &___
    0.51
     autorytatywna
    0.51
    DataPropertyName
    0.50
    семь
    0.50
    Activations Density 8.251%

    No Known Activations