© 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. 12248
    Prev
    Next
    INDEX
    Explanations

    text about people persevering through a difficult time

    oai_token-act-pair · gemini-2.0-flash

    current events

    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
    UserScript
    -0.60
     Covid
    -0.56
    Covid
    -0.56
    ]));
    -0.56
    resave
    -0.53
    INCREF
    -0.52
    plotly
    -0.52
    はじめに
    -0.52
     IndexPath
    -0.50
    CPtr
    -0.49
    POSITIVE LOGITS
     оригіналу
    0.64
     jsPsych
    0.53
     NUKAT
    0.50
    Jeografia
    0.50
     IFTT
    0.49
    adaptiveStyles
    0.49
    TagHelper
    0.49
    ГЛА
    0.49
     redé
    0.49
    govina
    0.49
    Activations Density 15.453%

    No Known Activations