© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12165
    Prev
    Next
    INDEX
    Explanations

    words and phrases to do with aiding or regulating.

    oai_token-act-pair · gemini-2.0-flash

    assist

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     assist
    -2.27
    Assist
    -2.14
     assisting
    -2.13
     assistance
    -2.11
     Assist
    -2.09
    assist
    -2.08
     assists
    -1.96
     Assistance
    -1.94
     assisted
    -1.88
    Assistance
    -1.85
    POSITIVE LOGITS
    0.46
    InMemory
    0.45
     Sp
    0.43
     Ch
    0.43
     W
    0.42
     Z
    0.41
    ఠ
    0.39
     sp
    0.39
    RequestContext
    0.39
     Macht
    0.39
    Activations Density 6.940%

    No Known Activations