© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13073
    Prev
    Next
    INDEX
    Explanations

    the start of the word "replicate/reproduce/represent"

    oai_token-act-pair · gemini-2.0-flash

    rep

    np_max-act · gemini-2.0-flash
    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
    ↵
    -0.88
    .
    -0.74
     and
    -0.72
     As
    -0.68
    ↵↵
    -0.66
     I
    -0.60
     seraient
    -0.60
    <eos>
    -0.59
    this
    -0.59
    ↵↵↵
    -0.59
    POSITIVE LOGITS
     photolibrary
    0.95
    moiselle
    0.94
    SharedDtor
    0.93
    duled
    0.90
     Forumite
    0.88
    ՚
    0.83
    ^(@)
    0.82
     crdi
    0.82
     Theſe
    0.81
     yoox
    0.80
    Activations Density 3.466%

    No Known Activations