© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11757
    Prev
    Next
    INDEX
    Explanations

    personal pronouns, words indicating people remaining in a group, and political structures.

    oai_token-act-pair · gemini-2.0-flash

    hold

    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
    setVerticalGroup
    -0.78
     jsPsych
    -0.55
    writeFieldEnd
    -0.52
    vallen
    -0.52
    最快更新
    -0.52
    tagHelperRunner
    -0.50
    Попис
    -0.49
     становника
    -0.49
    tanleria
    -0.49
    Launching
    -0.48
    POSITIVE LOGITS
     hold
    2.66
    hold
    2.41
     Hold
    2.38
     holding
    2.38
     holds
    2.30
     HOLD
    2.28
    Hold
    2.28
    HOLD
    2.19
     held
    2.17
    holding
    2.14
    Activations Density 2.648%

    No Known Activations