© 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. 1077
    Prev
    Next
    INDEX
    Explanations

    references to German language and grammar

    oai_token-act-pair · gemini-2.0-flash

    German text

    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
    findung
    -0.50
    TintMode
    -0.48
    igenschaften
    -0.48
    behör
    -0.47
    vertreter
    -0.46
    liesslich
    -0.46
    ilibre
    -0.44
    pheny
    -0.44
     usine
    -0.43
    wapV
    -0.43
    POSITIVE LOGITS
    featureID
    0.59
    StoryboardSegue
    0.59
    cektir
    0.58
    DialogComponent
    0.56
     willkommen
    0.56
    MLLoader
    0.55
    Personensuche
    0.54
     liebt
    0.54
    bolista
    0.54
    thodoxy
    0.54
    Activations Density 0.823%

    No Known Activations