© 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. 16076
    Prev
    Next
    INDEX
    Explanations

    text related to the 19th century and the relations involving Prussia and Austria

    oai_token-act-pair · gemini-2.0-flash

    Historical/political documents

    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
    RenderAtEndOf
    -0.84
     متعلقه
    -0.65
    XmlAccessType
    -0.60
     jsPsych
    -0.55
     nhiêu
    -0.51
    СР
    -0.51
    ThroughAttribute
    -0.51
    InstanceState
    -0.51
    InlineData
    -0.50
    %?
    -0.49
    POSITIVE LOGITS
     CreateTagHelper
    0.57
     الاطلاع
    0.56
    reportWebVitals
    0.54
     quæ
    0.53
     abſ
    0.52
     purpoſe
    0.52
     ſtate
    0.50
     auton
    0.50
     uſe
    0.49
     pleaſure
    0.49
    Activations Density 2.498%

    No Known Activations