© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15212
    Prev
    Next
    INDEX
    Explanations

    question mark followed by capitalized words, especially when describing a product.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    nologue
    -0.65
    postmedia
    -0.57
    balleur
    -0.56
    “
    -0.56
    hoeddwyd
    -0.55
    pidou
    -0.54
    зулта
    -0.53
     ویکی‌پدی
    -0.53
    janos
    -0.53
    batore
    -0.51
    POSITIVE LOGITS
    ThroughAttribute
    0.48
     Privacidade
    0.47
    AnchorStyles
    0.46
     BoxFit
    0.45
     onAnimation
    0.44
     solaire
    0.42
     user
    0.42
     Big
    0.42
    ServiceTest
    0.42
    uidado
    0.41
    Activations Density 2.004%

    No Known Activations