© 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. 8491
    Prev
    Next
    INDEX
    Explanations

    HTML anchors with associated special characters

    oai_token-act-pair · gemini-2.0-flash

    Code and foreign languages

    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
     pinulongan
    -0.54
    encodeWith
    -0.48
    GraphicsUnit
    -0.47
     imóvel
    -0.46
     ddelweddau
    -0.43
    ladin
    -0.43
     CBN
    -0.43
     Sikkim
    -0.41
     sahiptir
    -0.41
    RTEE
    -0.40
    POSITIVE LOGITS
    zdroj
    0.72
    ंदीखरीदारी
    0.66
    Hentet
    0.65
    zanie
    0.62
    źródło
    0.60
     الرياضيه
    0.59
     InputDecoration
    0.59
    FTFY
    0.59
    znak
    0.56
     ویکی‌پدیای
    0.56
    Activations Density 23.608%

    No Known Activations