© 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. 15095
    Prev
    Next
    INDEX
    Explanations

    quantities or measurement units, or the word "best"

    oai_token-act-pair · gemini-2.0-flash

    times, year

    np_max-act · gemini-2.0-flash

    times

    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
     week
    -0.58
     afield
    -0.56
    riller
    -0.54
    vember
    -0.54
     Majefty
    -0.52
    今週
    -0.50
     BnF
    -0.48
    week
    -0.48
    šech
    -0.48
     houſe
    -0.46
    POSITIVE LOGITS
    ❋
    0.68
    例句
    0.65
    NameInMap
    0.60
    ]})
    0.60
    )<<
    0.60
     consultato
    0.59
     Pictures
    0.59
     >=",
    0.57
    λου
    0.57
    ventus
    0.56
    Activations Density 2.039%

    No Known Activations