© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1902
    Prev
    Next
    INDEX
    Explanations

    academic text in economics or econometrics

    oai_token-act-pair · gemini-2.0-flash

    Research papers

    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
    AddTagHelper
    -0.73
    UnsafeEnabled
    -0.65
    nestjs
    -0.64
     MainAxisSize
    -0.64
    __*/
    -0.64
     насељу
    -0.60
     ddelweddau
    -0.60
    matchCondition
    -0.60
    AndEndTag
    -0.60
    Tikang
    -0.59
    POSITIVE LOGITS
    StructEnd
    0.59
    Abitanti
    0.48
     flyknit
    0.47
    Referências
    0.47
    Референце
    0.46
    inheit
    0.46
    Bare
    0.45
    入院
    0.45
    Wal
    0.44
     barren
    0.43
    Activations Density 3.665%

    No Known Activations