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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11246
    Prev
    Next
    INDEX
    Explanations

    terms related to the Democratic Republic of the Congo

    oai_token-act-pair · gemini-2.0-flash

    terms related to geographical names or entities

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

    out-of-context text

    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
     فريبيس
    -0.79
     myſelf
    -0.58
     itſelf
    -0.57
    Lähteet
    -0.55
    DotNetBar
    -0.54
     Hift
    -0.53
     ſtand
    -0.52
    OrWhiteSpace
    -0.51
    ñores
    -0.51
     fevere
    -0.50
    POSITIVE LOGITS
     EconPapers
    0.59
    Dichloropropane
    0.54
    ינוך
    0.51
    DNEY
    0.50
     kanton
    0.50
     tytu
    0.48
    ENCIES
    0.47
    ruik
    0.47
    mingen
    0.47
    IUrlHelper
    0.46
    Activations Density 0.249%

    No Known Activations