© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 4364
    Prev
    Next
    INDEX
    Explanations

    the word "the"

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act · gemini-2.0-flash

    the

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    tvguidetime
    -1.28
     utafitiHapana
    -1.02
    @[+][
    -0.90
     متعلقه
    -0.87
     ControllerBase
    -0.82
    Lähteet
    -0.82
     otomatig
    -0.81
    oredCriteria
    -0.81
     ब्रेकडाउन
    -0.79
    ValueStyle
    -0.78
    POSITIVE LOGITS
    <bos>
    1.69
    '
    1.10
    ↵↵
    1.05
    ’
    1.05
    <eos>
    0.91
    ↵
    0.81
    1
    0.64
    2
    0.64
    8
    0.62
    `
    0.60
    Activations Density 3.099%

    No Known Activations