© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12352
    Prev
    Next
    INDEX
    Explanations

    words ending in "l" that might be French

    oai_token-act-pair · gemini-2.0-flash

    Technical, multilingual code/text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    UnusedPrivate
    -0.76
     MonoBehaviour
    -0.75
    GenerationType
    -0.73
    ViewFeatures
    -0.71
     isolado
    -0.66
     InputDecoration
    -0.65
    mapreduce
    -0.65
     Shakspeare
    -0.64
    Liefs
    -0.64
    UrlResolution
    -0.63
    POSITIVE LOGITS
    al
    0.73
    <bos>
    0.71
    AL
    0.68
    nal
    0.66
    als
    0.66
    ally
    0.64
    IAL
    0.61
    ales
    0.59
    ial
    0.57
    ual
    0.57
    Activations Density 0.350%

    No Known Activations