© 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. 1125
    Prev
    Next
    INDEX
    Explanations

    German text, possibly related to grant funding and technical discussions

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    GEBURTS
    -0.69
     للاسماء
    -0.62
     تانيه
    -0.59
    GEBURTSDATUM
    -0.56
     soigne
    -0.50
    ImageContext
    -0.49
     AssemblyTitle
    -0.49
    ActionMode
    -0.49
     Besoin
    -0.48
     المعيارى
    -0.47
    POSITIVE LOGITS
    はじめに
    0.54
     sentimenti
    0.53
    JpaRepository
    0.52
     esimer
    0.49
     picioare
    0.49
     esimerkiksi
    0.49
     rotina
    0.48
     divertidos
    0.48
    quelize
    0.47
     kaupung
    0.47
    Activations Density 0.236%

    No Known Activations