© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4893
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gemini-2.0-flash

    expressions of gratitude

    np_token-act-pair-logits · gpt-4o-mini

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    पया
    -0.52
    mstyle
    -0.51
    หว่าง
    -0.48
     brig
    -0.47
    ठा
    -0.45
    far
    -0.44
     насеље
    -0.44
     astray
    -0.44
     Rptr
    -0.43
     Yourself
    -0.42
    POSITIVE LOGITS
    HostException
    0.79
    lapsingToolbar
    0.73
    ViewFeatures
    0.66
     for
    0.65
     very
    0.65
    ölker
    0.63
    encodeWith
    0.59
    BorderFactory
    0.59
    出版年
    0.57
    RenderAtEndOf
    0.56
    Activations Density 1.329%

    No Known Activations