© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4151
    Prev
    Next
    INDEX
    Explanations

    uses of the dot operator such as when accessing properties of objects in Java or similar languages

    oai_token-act-pair · gemini-2.0-flash

    programming syntax elements

    np_token-act-pair-logits · gpt-4o-mini
    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
    ]")]
    -0.63
    hyrchwyd
    -0.57
    ellido
    -0.56
     ویکی‌پدیا
    -0.56
    httphttps
    -0.54
    providedIn
    -0.54
     gynhyrchwyd
    -0.52
     сайті
    -0.51
     referenties
    -0.50
    atiles
    -0.50
    POSITIVE LOGITS
     '\\;'
    0.56
    IntoConstraints
    0.49
    Cie
    0.48
     >=",
    0.47
    raltar
    0.46
    település
    0.45
    dive
    0.44
     ◄
    0.43
     Taxonomic
    0.41
    loss
    0.41
    Activations Density 0.824%

    No Known Activations