© 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. 9896
    Prev
    Next
    INDEX
    Explanations

    the words "directed" and "see" or forms of "see"

    oai_token-act-pair · gemini-2.0-flash

    see

    np_max-act · gemini-2.0-flash

    see

    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
    mær
    -0.58
     meille
    -0.57
     visuelle
    -0.54
     jäsen
    -0.54
     aşağı
    -0.53
    ratulations
    -0.53
    ')}}">
    -0.53
     yourselves
    -0.52
    Дереккөздер
    -0.52
    DockStyle
    -0.51
    POSITIVE LOGITS
    <bos>
    0.87
    contentLoaded
    0.82
     propOrder
    0.74
    RegressionTest
    0.73
    itisation
    0.69
     favours
    0.66
     <<<<<<<<<<<<<<
    0.66
     ExecuteAsync
    0.66
    homonymie
    0.65
     fuelled
    0.65
    Activations Density 0.115%

    No Known Activations