© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8164
    Prev
    Next
    INDEX
    Explanations

    a mishmash of generally common words, often related to mechanics or programming, as well as answers in a Q&A format.

    oai_token-act-pair · gemini-2.0-flash

    Question/answer dialogue

    np_max-act · gemini-2.0-flash
    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
    -1.17
     myſelf
    -1.06
    ^(@)
    -1.01
     iſt
    -0.97
    ſelf
    -0.94
     $_"
    -0.90
     ſche
    -0.85
    ValueStyle
    -0.84
     ſeveral
    -0.84
    @[+][
    -0.83
    POSITIVE LOGITS
    ↵↵
    0.93
    .
    0.83
    ↵↵↵
    0.78
     The
    0.75
    ↵
    0.73
     In
    0.60
     .
    0.60
    </sub>
    0.58
     “
    0.58
    </h3>
    0.57
    Activations Density 6.800%

    No Known Activations