© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12321
    Prev
    Next
    INDEX
    Explanations

    text about the video game NBA 2K.

    oai_token-act-pair · gemini-2.0-flash

    internet slang

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    Vidite
    -0.69
     Efq
    -0.64
     Shakspeare
    -0.62
    tvguidetime
    -0.61
     MessageBoxIcon
    -0.60
     ſever
    -0.59
     GetEnumerator
    -0.59
     Ngb
    -0.58
    SpringBootTest
    -0.57
     Moslem
    -0.57
    POSITIVE LOGITS
     u
    0.91
     r
    0.82
     U
    0.71
     iz
    0.70
     w
    0.70
     lyk
    0.68
     ur
    0.67
     b
    0.63
    vr
    0.61
     juz
    0.61
    Activations Density 0.928%

    No Known Activations