Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12108
    Prev
    Next
    INDEX
    Explanations

    Danish words or phrases from HTML code

    oai_token-act-pair · gemini-2.0-flash

    non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    AndEndTag
    -0.53
     <=",
    -0.48
    phrine
    -0.46
    Према
    -0.44
    madol
    -0.44
    glected
    -0.43
    ydon
    -0.42
    XmlAccessorType
    -0.41
    énario
    -0.40
    бль
    -0.40
    POSITIVE LOGITS
     Ooster
    0.56
    saraba
    0.56
    HtmlAttribute
    0.55
     myſelf
    0.53
     juges
    0.51
    +:+
    0.51
    Personendaten
    0.50
     Monfieur
    0.50
     kleid
    0.50
    inaison
    0.50
    Activations Density 0.199%

    No Known Activations