© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4166
    Prev
    Next
    INDEX
    Explanations

    grammatical structures and verbs in German

    oai_token-act-pair · gemini-2.0-flash

    specific modal verbs

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

    German language

    np_max-act-logits · gemini-2.0-flash
    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
    naker
    -0.48
    delegate
    -0.42
     "..\..\..\
    -0.42
    НАЯ
    -0.41
    MockMvc
    -0.39
     DPR
    -0.39
    AddTagHelper
    -0.39
    Segue
    -0.39
    gway
    -0.39
     bandar
    -0.39
    POSITIVE LOGITS
     مرئيه
    0.68
     AssemblyCulture
    0.68
    msgTypes
    0.68
    ViewFeatures
    0.66
    iastes
    0.64
     وتسجيلات
    0.63
     désolés
    0.63
    CPtr
    0.62
     مشين
    0.59
    ագրություններ
    0.59
    Activations Density 0.188%

    No Known Activations