© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5474
    Prev
    Next
    INDEX
    Explanations

    time frames prefaced with numbers or adjectives

    oai_token-act-pair · gemini-2.0-flash

    hour

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     kasarigan
    -0.69
    }))
    -0.64
    apunov
    -0.60
    chyma
    -0.59
     Corbu
    -0.56
    cidae
    -0.54
     Pulsar
    -0.54
     OnTrigger
    -0.54
    brainly
    -0.54
    uitton
    -0.54
    POSITIVE LOGITS
     five
    0.80
    five
    0.74
     six
    0.71
     seven
    0.66
     four
    0.66
    four
    0.66
    six
    0.64
     three
    0.62
     cinq
    0.61
     eight
    0.61
    Activations Density 1.991%

    No Known Activations