© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8818
    Prev
    Next
    INDEX
    Explanations

    German modal verbs, especially "hätte," and other common German words related to sentence structure plus some English names.

    oai_token-act-pair · gemini-2.0-flash

    Scandinavian languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    trui
    -0.46
    casian
    -0.43
    opcional
    -0.43
     plastiques
    -0.43
    OGRAPH
    -0.41
    nių
    -0.41
     trouvez
    -0.40
    EROUS
    -0.40
    ={()=>
    -0.40
     financières
    -0.40
    POSITIVE LOGITS
    ürze
    0.69
    öhnen
    0.68
    ünst
    0.68
    ühnen
    0.67
    öpfe
    0.67
    ække
    0.66
    öpf
    0.66
    ähne
    0.65
    ärsk
    0.64
    äume
    0.63
    Activations Density 2.540%

    No Known Activations