© 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. 15937
    Prev
    Next
    INDEX
    Explanations

    language from physics papers, specially superconductivity

    oai_token-act-pair · gemini-2.0-flash

    superconductivity

    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
    RegressionTest
    -0.66
    jsp
    -0.49
    scalatest
    -0.47
    WIS
    -0.46
     run
    -0.44
     cô
    -0.42
    bolo
    -0.42
    TRANS
    -0.42
    wis
    -0.42
     mag
    -0.42
    POSITIVE LOGITS
     referenties
    0.71
    новниш
    0.65
    ReusableCell
    0.65
     giustizia
    0.64
    elemField
    0.61
    پیوند
    0.60
     démocr
    0.59
    ImageContext
    0.59
     publiques
    0.58
    StructEnd
    0.58
    Activations Density 5.327%

    No Known Activations