© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6353
    Prev
    Next
    INDEX
    Explanations

    phrases "a [ADJECTIVE] [NOUN]", "is a" as well as some words related to morality and religion.

    oai_token-act-pair · gemini-2.0-flash

    a/as

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    \}^{
    -0.71
    Weblinks
    -0.68
     Majefty
    -0.68
     GenerationType
    -0.64
    Hochspringen
    -0.63
    Sucesor
    -0.61
    XmlAccessType
    -0.61
    lccn
    -0.59
     ―――――
    -0.59
     todd
    -0.57
    POSITIVE LOGITS
    RenderAtEndOf
    0.57
     celebration
    0.55
     tribute
    0.45
     conversation
    0.45
     upaya
    0.44
     D
    0.43
     expression
    0.43
     homage
    0.42
    omen
    0.42
     statement
    0.41
    Activations Density 0.960%

    No Known Activations