© 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. 13929
    Prev
    Next
    INDEX
    Explanations

    mentions of Denver Colorado relative to other cities

    oai_token-act-pair · 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
     ↑
    -0.47
     quad
    -0.46
     الاطلاع
    -0.42
    功
    -0.41
     held
    -0.40
    makeConstraints
    -0.40
    太
    -0.40
    IsSet
    -0.39
    мә
    -0.39
     kuid
    -0.38
    POSITIVE LOGITS
    Einzelnachweise
    0.74
    קישורים
    0.68
    campal
    0.68
    bekistan
    0.65
    tagHelperRunner
    0.63
    kuuta
    0.62
    omock
    0.62
     Ceinture
    0.61
     فريبيس
    0.61
    akterysty
    0.60
    Activations Density 0.302%

    No Known Activations