© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2658
    Prev
    Next
    INDEX
    Explanations

    words and phrases from corporate mission statements, especially those related to pharmaceuticals

    oai_token-act-pair · gemini-2.0-flash

    special characters and HTML-like syntax

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

    general information

    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
    $\
    -0.58
    of
    -0.57
    op
    -0.55
    me
    -0.54
    on
    -0.54
    fre
    -0.54
    ese
    -0.54
    to
    -0.54
    P
    -0.53
    re
    -0.52
    POSITIVE LOGITS
    expandindo
    1.20
    ^(@)
    1.05
    __":
    1.05
     esternos
    1.04
    AddHtmlAttribute
    1.02
    🏻‍♀️
    1.02
    yntaxException
    1.02
    '},
    0.97
    脚注の使い方
    0.97
    __':
    0.96
    Activations Density 7.578%

    No Known Activations