© 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. 12975
    Prev
    Next
    INDEX
    Explanations

    the word "drama" as well as words associated with film/television production

    oai_token-act-pair · gemini-2.0-flash

    drama

    np_max-act · gemini-2.0-flash

    ▁drama

    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
    <bos>
    -1.12
    eſt
    -0.71
     EnglishChoose
    -0.70
     iſt
    -0.69
    ſhip
    -0.68
     ―――――
    -0.68
    ัติ
    -0.67
    ingeki
    -0.65
    "]);
    -0.63
    ]})
    -0.61
    POSITIVE LOGITS
     vectorielles
    0.94
     termica
    0.86
     normaux
    0.82
     nemici
    0.81
     traditionnels
    0.80
     religieuses
    0.80
     nemico
    0.80
     acoper
    0.79
     viață
    0.76
     noemen
    0.76
    Activations Density 1.244%

    No Known Activations