© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11510
    Prev
    Next
    INDEX
    Explanations

    code snippets and legal/political jargon

    oai_token-act-pair · gemini-2.0-flash

    for. Method used: 1. Reason: the MAX_ACTIVATING_TOKEN is the word "for", and since the tokens are sometimes case sensitive, there is a "For" in the max activating tokens as well.for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    yanto
    -0.60
    ICAGO
    -0.59
    BRUARY
    -0.56
    unately
    -0.56
     emel
    -0.55
    \<^
    -0.54
    ighbor
    -0.54
    ineſs
    -0.53
     partea
    -0.53
    IFORNIA
    -0.53
    POSITIVE LOGITS
    AddTagHelper
    1.15
     ModelExpression
    1.03
    aarrggbb
    0.95
    ValueStyle
    0.92
     <=",
    0.89
     kasarigan
    0.89
     ddelweddau
    0.88
     المعيارى
    0.88
    AddHtmlAttribute
    0.88
     surla
    0.86
    Activations Density 7.327%

    No Known Activations