© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7482
    Prev
    Next
    INDEX
    Explanations

    mentions of Germany including its political elements and geography

    oai_token-act-pair · gemini-2.0-flash

    references to Germany and its regions

    np_token-act-pair-logits · gpt-4o-mini

    Germany and West Germany

    np_max-act-logits · gemini-2.0-flash

    West

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     CreateTagHelper
    -0.66
    tableFuture
    -0.58
     szóci
    -0.57
    ImageContext
    -0.54
    外部連結
    -0.54
    urangi
    -0.54
    leman
    -0.53
     دیکھیے
    -0.53
     mihi
    -0.52
    SizeMode
    -0.51
    POSITIVE LOGITS
     West
    0.91
    West
    0.85
     German
    0.74
     WEST
    0.68
    German
    0.62
    WEST
    0.60
     Germany
    0.59
    west
    0.55
     Réponses
    0.54
    httphttps
    0.54
    Activations Density 2.302%

    No Known Activations