© 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. 12718
    Prev
    Next
    INDEX
    Explanations

    words related to government decisions, code, or abstract actions

    oai_token-act-pair · gemini-2.0-flash

    non-English words or technical terms

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

    Code/technical text

    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
    (
    -0.60
    <eos>
    -0.51
    A
    -0.51
    D
    -0.51
    ↵
    -0.50
    ::
    -0.49
    T
    -0.48
    E
    -0.47
     ein
    -0.46
    .(
    -0.46
    POSITIVE LOGITS
     Forumite
    0.99
    IntoConstraints
    0.97
     ―――――
    0.94
    Билгалдахарш
    0.93
    ^(@)
    0.92
    Дереккөздер
    0.90
     ་་
    0.89
    RegressionTest
    0.89
     autorytatywna
    0.88
    NUMX
    0.88
    Activations Density 13.030%

    No Known Activations