© 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. 16292
    Prev
    Next
    INDEX
    Explanations

    both Spanish and Javascript programming terms

    oai_token-act-pair · gemini-2.0-flash

    variations of "su"

    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
     his
    -1.16
     her
    -0.97
     their
    -0.92
    his
    -0.81
    their
    -0.74
     its
    -0.73
    His
    -0.67
     His
    -0.66
     kanyang
    -0.63
    他的
    -0.63
    POSITIVE LOGITS
     su
    2.50
     sus
    1.91
    Su
    1.69
    su
    1.64
     Su
    1.54
     SU
    1.48
    sus
    1.45
    Sus
    1.41
     Sus
    1.38
     SUS
    1.23
    Activations Density 0.544%

    No Known Activations