© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8211
    Prev
    Next
    INDEX
    Explanations

    the letters C and D, mostly in association with scientific publications

    oai_token-act-pair · gemini-2.0-flash

    D

    np_max-act · gemini-2.0-flash
    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
    styleType
    -0.82
    onaceous
    -0.81
    archiviato
    -0.78
    etheless
    -0.76
    BibitemShut
    -0.76
    〢
    -0.74
     OkHttpClient
    -0.74
    }))
    -0.74
    strtotime
    -0.74
    orithmic
    -0.74
    POSITIVE LOGITS
    SequentialGroup
    0.80
    b
    0.57
    A
    0.54
    B
    0.53
    <bos>
    0.53
     Paglinawan
    0.52
    D
    0.52
    ↵
    0.49
     habet
    0.49
    Key
    0.48
    Activations Density 2.152%

    No Known Activations