© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11257
    Prev
    Next
    INDEX
    Explanations

    fairly common function words and articles, such as "the", "of", "a", "in", etc, and links to women's motocross

    oai_token-act-pair · gemini-2.0-flash

    technical terms or programming concepts

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

    sports competition

    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
     direto
    -0.50
     ritrov
    -0.44
    pokem
    -0.42
     Serikat
    -0.42
     urmă
    -0.40
     IntPtr
    -0.39
     šal
    -0.39
    __
    -0.39
    Getenv
    -0.39
     Genel
    -0.38
    POSITIVE LOGITS
     CreateTagHelper
    0.85
    MessageTagHelper
    0.77
    oa̍t
    0.75
     useStyles
    0.75
     NSCoder
    0.69
     Administrativna
    0.69
    AndEndTag
    0.66
    reactstrap
    0.64
    oplayer
    0.63
    PyExc
    0.63
    Activations Density 2.943%

    No Known Activations