© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13360
    Prev
    Next
    INDEX
    Explanations

    a mix of different types of contexts, activating on different topics but often with a personal or first-person element.

    oai_token-act-pair · gemini-2.0-flash

    cells and bones

    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
     Италијани
    -0.91
     nakalista
    -0.89
     leaſt
    -0.87
    djangoproject
    -0.84
     pleaſure
    -0.81
     ſeveral
    -0.80
     ſtate
    -0.79
     houſe
    -0.78
     Majefty
    -0.78
     poffible
    -0.77
    POSITIVE LOGITS
     sed
    0.48
     del
    0.47
    meli
    0.45
    <eos>
    0.45
     led
    0.44
    METAL
    0.44
    libri
    0.43
     res
    0.43
    KommentareTeilen
    0.43
    vrier
    0.42
    Activations Density 5.530%

    No Known Activations