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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8794
    Prev
    Next
    INDEX
    Explanations

    non-English characters and labels in mathematical equations (likely from scientific publications)

    oai_token-act-pair · gemini-2.0-flash

    Code/Foreign words

    np_max-act-logits · 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
    νή
    -0.63
     himo
    -0.60
    άζ
    -0.59
    άν
    -0.56
    IBOutlet
    -0.54
    νώ
    -0.52
    XmlAccessType
    -0.52
    ική
    -0.51
    όμε
    -0.51
    έρ
    -0.50
    POSITIVE LOGITS
    NamedQueries
    0.59
    MENAFN
    0.58
    στημα
    0.57
    setOpaque
    0.57
    σεων
    0.56
    VersionUID
    0.55
    νονται
    0.54
    θηκαν
    0.53
    οντας
    0.52
    ξης
    0.51
    Activations Density 1.717%

    No Known Activations