© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4919
    Prev
    Next
    INDEX
    Explanations

    technical terms relating to computer networks

    oai_token-act-pair · gemini-2.0-flash

    technical network terms or identifiers

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

    network

    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
     disambiguazione
    -0.82
     المعيارى
    -0.73
     digitais
    -0.54
    UpInside
    -0.53
    Spoljašnje
    -0.53
    abestanden
    -0.52
    AndroidJUnit
    -0.51
    kuuta
    -0.50
    multer
    -0.49
    KommentareTeilen
    -0.49
    POSITIVE LOGITS
    </thead>
    0.56
    Matin
    0.54
    ExecuteNonQuery
    0.52
    िखित
    0.52
     سكانية
    0.52
    fml
    0.50
     overflow
    0.50
     Repe
    0.49
     början
    0.49
    colhead
    0.49
    Activations Density 2.555%

    No Known Activations