© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9150
    Prev
    Next
    INDEX
    Explanations

    the programming language C++ and the medical procedure C-section

    oai_token-act-pair · gemini-2.0-flash

    medical procedures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Datuak
    -0.85
    UrlResolution
    -0.75
     ModelExpression
    -0.75
    CodedInputStream
    -0.69
    ernalia
    -0.69
    tvguidetime
    -0.69
    abetes
    -0.66
     nakalista
    -0.63
    RTDA
    -0.63
    xase
    -0.62
    POSITIVE LOGITS
     Caesar
    0.87
    Caesar
    0.79
     Caesars
    0.61
     Caes
    0.59
    arean
    0.58
    ailangan
    0.54
     Cesar
    0.52
    soever
    0.51
     Cæsar
    0.50
     Cau
    0.50
    Activations Density 0.361%

    No Known Activations