© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10801
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with conditional statements, instructions, and dependencies.

    oai_token-act-pair · gemini-2.0-flash

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    SourceChecksum
    -0.79
    يميديا
    -0.73
    <bos>
    -0.72
    WriteTagHelper
    -0.71
    :✨
    -0.70
    AndEndTag
    -0.69
     للاسماء
    -0.68
     itſelf
    -0.68
     >=",
    -0.66
     nahilalakip
    -0.66
    POSITIVE LOGITS
    ass
    0.53
     günü
    0.49
     Ass
    0.48
    ApiOperation
    0.47
    гла
    0.46
    OwnProperty
    0.46
    XMLSchema
    0.46
    ora
    0.46
    ----------------
    0.45
    low
    0.45
    Activations Density 3.254%

    No Known Activations