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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13822
    Prev
    Next
    INDEX
    Explanations

    numbers, especially years, and words connected to them

    oai_token-act-pair · gemini-2.0-flash

    say "0"

    np_max-act-logits · gemini-2.0-flash

    digits

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     ་་
    -1.04
    leſs
    -0.94
    }}]{
    -0.93
    ]--;
    -0.93
     Houſe
    -0.91
     nahilalakip
    -0.90
    neſs
    -0.89
    FTFY
    -0.89
    ஧
    -0.88
    <unused22>
    -0.88
    POSITIVE LOGITS
    ########.
    0.04
     InputDecoration
    0.04
     مرئيه
    -0.00
    uxxxx
    -0.02
     esternos
    -0.06
    orianCalendar
    -0.07
     يتيمه
    -0.07
     AssemblyTitle
    -0.09
     EconPapers
    -0.09
    URLException
    -0.10
    Activations Density 24.109%

    No Known Activations