© 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. 11036
    Prev
    Next
    INDEX
    Explanations

    news article snippets, specifically bullet points with associated information from a news source

    oai_token-act-pair · gemini-2.0-flash

    News updates

    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
     
    -0.94
    <eos>
    -0.79
     I
    -0.70
    ,
    -0.63
    ...
    -0.59
     the
    -0.59
    ↵
    -0.57
     but
    -0.57
     i
    -0.55
     and
    -0.55
    POSITIVE LOGITS
     pleaſure
    1.12
     myſelf
    1.08
     greateſt
    1.07
     Efq
    1.03
     Jefus
    1.03
     purpoſe
    1.00
     itſelf
    1.00
     raiſ
    1.00
     himſelf
    1.00
     uſed
    0.99
    Activations Density 0.752%

    No Known Activations