© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10088
    Prev
    Next
    INDEX
    Explanations

    numbers and related symbols (., A)

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ConfigureAwait
    -0.54
    ka
    -0.54
    hl
    -0.52
     te
    -0.49
     some
    -0.49
    DeleteBehavior
    -0.48
    <eos>
    -0.48
    enumi
    -0.48
     k
    -0.47
    bi
    -0.47
    POSITIVE LOGITS
     pleaſure
    1.07
     purpoſe
    1.04
     ſche
    0.96
     ſtate
    0.95
     itſelf
    0.94
     Efq
    0.91
     becauſe
    0.90
     ſta
    0.90
     raiſ
    0.89
     Majefty
    0.87
    Activations Density 0.584%

    No Known Activations