© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 646
    Prev
    Next
    INDEX
    Explanations

    references to locations in Schleswig-Holstein, especially with Danish spellings and abbreviations

    oai_token-act-pair · gemini-2.0-flash

    Danish history/places

    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
     will
    -0.41
    oara
    -0.41
     x
    -0.40
     ao
    -0.40
     y
    -0.40
     die
    -0.40
    ERTA
    -0.40
     worry
    -0.39
     OF
    -0.39
     hard
    -0.39
    POSITIVE LOGITS
     skolen
    0.94
     skolan
    0.94
     étoient
    0.94
     démocr
    0.94
     varandra
    0.90
     medlemmer
    0.87
     stället
    0.86
    Personensuche
    0.85
     étoit
    0.85
     négociations
    0.85
    Activations Density 4.594%

    No Known Activations