© 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. 16074
    Prev
    Next
    INDEX
    Explanations

    medical terminology and related words such as "common", and "affected"

    oai_token-act-pair · gemini-2.0-flash

    is or are

    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
     <>",
    -0.88
    帖最后由
    -0.81
     propOrder
    -0.80
     Савезне
    -0.78
    GEBURTSDATUM
    -0.77
     onAnimation
    -0.76
    +#+#
    -0.76
     Réponses
    -0.75
    Personendaten
    -0.70
     للاسماء
    -0.69
    POSITIVE LOGITS
     nam
    0.48
    olli
    0.46
    AdapterFactory
    0.44
     char
    0.44
    ука
    0.44
     cork
    0.43
    cdnjs
    0.43
     cu
    0.42
     drug
    0.42
     Ray
    0.42
    Activations Density 3.315%

    No Known Activations