Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16120
    Prev
    Next
    INDEX
    Explanations

    references to a person's spouse and immediate family

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    mybatisplus
    -0.75
     MongoClient
    -0.71
     resourceCulture
    -0.71
    PDOException
    -0.70
    __":
    -0.70
    SBATCH
    -0.69
     we
    -0.65
     undersigned
    -0.65
    
    -0.64
    منم
    -0.63
    POSITIVE LOGITS
     and
    1.16
    和
    0.51
    力和
    0.50
     и
    0.48
    性和
    0.47
    IBOutlet
    0.45
     scolaires
    0.43
    子和
    0.42
     virtuales
    0.42
     và
    0.42
    Activations Density 0.394%

    No Known Activations