© 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. 2142
    Prev
    Next
    INDEX
    Explanations

    "don't", "isn't", "doesn't", "haven't", and "aren't"

    oai_token-act-pair · gemini-2.0-flash

    Negative contractions

    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
     démocr
    -0.74
     ouvriers
    -0.72
     fédé
    -0.71
    ssf
    -0.71
     sauvages
    -0.71
    sb
    -0.71
     européens
    -0.69
    sc
    -0.67
     prisonniers
    -0.67
    sp
    -0.65
    POSITIVE LOGITS
     itſelf
    0.74
     myſelf
    0.71
    ’”
    0.69
    ՚
    0.60
     iſt
    0.60
     XNUMX
    0.59
    ’?
    0.58
     ſind
    0.54
    ”?
    0.54
     raiſ
    0.54
    Activations Density 0.728%

    No Known Activations