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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12888
    Prev
    Next
    INDEX
    Explanations

    information about Korean television broadcasting, especially names, dates and times

    oai_token-act-pair · gemini-2.0-flash

    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
    ngrx
    -0.62
    XmlAccessType
    -0.60
     Italijanski
    -0.55
     Roskov
    -0.50
     uska
    -0.48
     Bourgoin
    -0.48
    aryng
    -0.47
     considérons
    -0.47
    soort
    -0.46
    "]}
    -0.46
    POSITIVE LOGITS
    MENAFN
    0.62
    icorn
    0.53
    ContentAsync
    0.52
     murale
    0.51
    ньому
    0.51
     japonais
    0.47
    makeText
    0.47
     japanese
    0.46
     Tokyo
    0.46
    脚注の使い方
    0.46
    Activations Density 5.662%

    No Known Activations