© 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. 4055
    Prev
    Next
    INDEX
    Explanations

    words related to materials and hardware

    oai_token-act-pair · gemini-2.0-flash

    materials

    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
     avoient
    -0.88
     ſmall
    -0.80
     enfans
    -0.79
     itſelf
    -0.77
     iſt
    -0.75
     ainfi
    -0.75
     étoient
    -0.75
     feroit
    -0.73
     prisonniers
    -0.73
     démocr
    -0.72
    POSITIVE LOGITS
    ngOnDestroy
    0.47
    pitaux
    0.44
    -
    0.44
    jface
    0.43
    enumi
    0.43
    繹
    0.43
    ,
    0.43
    .
    0.42
    ous
    0.41
    pa
    0.41
    Activations Density 3.109%

    No Known Activations