© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14807
    Prev
    Next
    INDEX
    Explanations

    german text about modal verbs and related concepts, specifically dealing with forming complex sentences with multiple verbs

    oai_token-act-pair · gemini-2.0-flash

    German with many verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -0.81
    <eos>
    -0.55
     the
    -0.55
     in
    -0.54
    h
    -0.54
     peny
    -0.53
    com
    -0.50
     that
    -0.50
      
    -0.48
     C
    -0.48
    POSITIVE LOGITS
    setVerticalGroup
    0.93
     AssemblyCulture
    0.92
    PreferredItem
    0.91
     المعيارى
    0.91
     EconPapers
    0.88
     Efq
    0.84
    ^(@)
    0.84
     cdti
    0.83
    protoimpl
    0.82
     ujednoznacz
    0.81
    Activations Density 0.106%

    No Known Activations