© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4839
    Prev
    Next
    INDEX
    Explanations

    language around the concept of enjoyment, benefit, or intent

    oai_token-act-pair · gemini-2.0-flash

    technical terms or programming keywords

    np_token-act-pair-logits · gpt-4o-mini

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     polaire
    -0.73
     Romains
    -0.62
     alimentaire
    -0.61
     poffible
    -0.61
     <=",
    -0.61
     wikipagina
    -0.57
    wechs
    -0.57
     médié
    -0.57
     Crocker
    -0.56
     normaux
    -0.56
    POSITIVE LOGITS
     initComponents
    0.56
    FailureListener
    0.50
    FilterChain
    0.48
    VersionUID
    0.47
    esgue
    0.47
     createContext
    0.42
     impress
    0.42
    eep
    0.41
     Зак
    0.41
     burn
    0.40
    Activations Density 0.998%

    No Known Activations