© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5040
    Prev
    Next
    INDEX
    Explanations

    the word "parts"

    oai_token-act-pair · gemini-2.0-flash

    parts

    np_max-act · gemini-2.0-flash

    parts

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     Efq
    -0.91
     Monfieur
    -0.88
     "..\..\
    -0.86
    ourite
    -0.86
    SpringRunner
    -0.84
     "..\..\..\
    -0.84
     pleaſure
    -0.83
     raiſ
    -0.82
     leaſt
    -0.79
     Sarm
    -0.78
    POSITIVE LOGITS
     of
    0.80
    ’
    0.74
     part
    0.71
     l
    0.62
     es
    0.61
    ()])
    0.59
     der
    0.59
    mybatisplus
    0.59
     dis
    0.58
    ’,
    0.58
    Activations Density 2.000%

    No Known Activations