© 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. 8585
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "font-weight: bold" or similar phrases pertaining to bold fonts, and also the color red

    oai_token-act-pair · gemini-2.0-flash

    programming concepts or UI components

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

    Code/text formatting

    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
    WebServlet
    -0.69
     szóci
    -0.63
    fillType
    -0.56
    awtextra
    -0.56
     تضيفلها
    -0.55
    })()
    -0.54
    Personendaten
    -0.54
     langsung
    -0.52
    )");
    -0.52
    gdx
    -0.51
    POSITIVE LOGITS
    migrationBuilder
    0.52
     owner
    0.51
     owners
    0.47
     conjugation
    0.47
     Sosten
    0.47
     abbraccio
    0.46
    ping
    0.46
     root
    0.46
    UIControlState
    0.46
    b
    0.45
    Activations Density 0.281%

    No Known Activations