© 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. 4012
    Prev
    Next
    INDEX
    Explanations

    mentions of time within a sports context

    oai_token-act-pair · gemini-2.0-flash

    half

    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
     GenerationType
    -0.91
    __':
    -0.90
    __":
    -0.86
     Theſe
    -0.80
    __':
    -0.77
     nicest
    -0.75
    <bos>
    -0.75
     otomatig
    -0.74
    StoryboardSegue
    -0.73
    viewWillAppear
    -0.72
    POSITIVE LOGITS
    anmoins
    0.60
     ['
    0.56
    cio
    0.55
    ["
    0.54
    pel
    0.53
    רה
    0.53
    之下
    0.52
     [
    0.52
     Just
    0.51
    ais
    0.51
    Activations Density 0.315%

    No Known Activations