© 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. 4972
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols presented in a variety of formats

    oai_token-act-pair · gemini-2.0-flash

    programming syntax elements or code-related terms

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

    2

    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
    rrggbb
    -0.75
     linkovi
    -0.64
     незавершена
    -0.63
    __':
    -0.63
    Datuak
    -0.62
     تضيفلها
    -0.59
     الرياضيه
    -0.59
    ]--;
    -0.57
     وتسجيلات
    -0.56
    matum
    -0.55
    POSITIVE LOGITS
     jScrollPane
    0.56
    #+#
    0.52
    nd
    0.52
    CPtr
    0.49
    4
    0.48
    GtkWidget
    0.43
     paramInt
    0.43
     DbContext
    0.43
     Händen
    0.43
    Espèce
    0.43
    Activations Density 21.136%

    No Known Activations