© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13618
    Prev
    Next
    INDEX
    Explanations

    German words related to sentence structure and complexity

    oai_token-act-pair · gemini-2.0-flash

    German "and"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     automatiques
    -0.43
    moveToFirst
    -0.42
     devons
    -0.42
    ianto
    -0.42
    tehen
    -0.42
     ahor
    -0.40
     quelcon
    -0.40
     âgées
    -0.40
     e
    -0.39
     negra
    -0.39
    POSITIVE LOGITS
     und
    2.22
     Und
    1.73
    Und
    1.69
    und
    1.59
     UND
    1.50
    UND
    1.09
     vnd
    1.03
     oder
    0.91
    unds
    0.87
     undis
    0.84
    Activations Density 1.064%

    No Known Activations