© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10142
    Prev
    Next
    INDEX
    Explanations

    words related to investigation and analysis within written works

    oai_token-act-pair · gemini-2.0-flash

    discuss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     discussion
    -1.80
     Discussion
    -1.66
     discuss
    -1.63
     discussed
    -1.58
    discussion
    -1.56
    Discussion
    -1.54
     discussing
    -1.53
     discussions
    -1.47
     DISCUSSION
    -1.45
     discusses
    -1.43
    POSITIVE LOGITS
     وتسجيلات
    0.70
    ftagPool
    0.66
    цезда
    0.66
     ujednoznacz
    0.63
    AndEndTag
    0.62
     تانيه
    0.62
     صوتيه
    0.61
    IsContent
    0.60
     Wikimedijinoj
    0.56
     LoggerFactory
    0.56
    Activations Density 1.713%

    No Known Activations