© 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. 6121
    Prev
    Next
    INDEX
    Explanations

    instances of the word "poll", as well as words that often appear with it such as "vote", and "University"

    oai_token-act-pair · gemini-2.0-flash

    poll

    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
    LookAnd
    -0.82
    IntoConstraints
    -0.75
    RenderAtEndOf
    -0.74
     propOrder
    -0.71
    AutoScaleMode
    -0.70
    帖最后由
    -0.65
    \{\\
    -0.64
     newOwner
    -0.63
    berdayakan
    -0.62
    queryInterface
    -0.61
    POSITIVE LOGITS
    Cordialement
    0.56
    التالي
    0.56
     Cosmos
    0.56
     gynhyrchwyd
    0.52
     spiegel
    0.52
     !}
    0.51
     BigInt
    0.50
     Cagliari
    0.49
     jir
    0.49
     Beers
    0.49
    Activations Density 0.706%

    No Known Activations