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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5520
    Prev
    Next
    INDEX
    Explanations

    superlatives with positive connotations as well as words with middling positive associations.

    oai_token-act-pair · gemini-2.0-flash

    best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     فريبيس
    -0.56
     pobla
    -0.54
     Besten
    -0.53
    marginHorizontal
    -0.53
    ētu
    -0.52
     best
    -0.50
     ویکی‌پدیا
    -0.49
    तः
    -0.48
     quanto
    -0.48
    ley
    -0.48
    POSITIVE LOGITS
    raszamy
    0.85
     sceptical
    0.73
    ourites
    0.65
     specialises
    0.65
     spoilt
    0.63
     favourites
    0.63
     specialise
    0.63
     scepticism
    0.63
     specialising
    0.63
    rolment
    0.62
    Activations Density 0.911%

    No Known Activations