© 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. 13320
    Prev
    Next
    INDEX
    Explanations

    vocabulary related to the organization, operations, and output of events and research

    oai_token-act-pair · gemini-2.0-flash

    Occupations

    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
     للاسماء
    -0.97
     فريبيس
    -0.94
     resourceCulture
    -0.93
    OGND
    -0.81
    ValueStyle
    -0.78
     cherchés
    -0.77
    expandindo
    -0.74
     poveznice
    -0.74
     tartalomajánló
    -0.73
    verwijspagina
    -0.72
    POSITIVE LOGITS
     who
    0.93
    who
    0.59
     Who
    0.57
     whom
    0.57
    whom
    0.56
    imageshack
    0.52
     nærm
    0.48
    Who
    0.48
     whether
    0.46
     in
    0.45
    Activations Density 9.767%

    No Known Activations