© 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. 12007
    Prev
    Next
    INDEX
    Explanations

    references to time, especially centuries and decades, signaled by words like "by," "of," "in", "late", "around", and "until".

    oai_token-act-pair · gemini-2.0-flash

    references to centuries

    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
     autorytatywna
    -1.12
     resourceCulture
    -0.96
    JspWriter
    -0.90
    évaluateur
    -0.81
     defaultstate
    -0.81
    HomeAsUpEnabled
    -0.80
    TintMode
    -0.80
    StructEnd
    -0.79
    قایناق‌لار
    -0.75
    IsMutable
    -0.74
    POSITIVE LOGITS
    II
    0.52
     secretario
    0.43
    Our
    0.42
    III
    0.42
    Y
    0.41
    XI
    0.41
    X
    0.41
     II
    0.40
    gs
    0.40
     nossos
    0.40
    Activations Density 1.343%

    No Known Activations