© 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. 13627
    Prev
    Next
    INDEX
    Explanations

    words or phrases that are interesting while slightly preferring scientific publications

    oai_token-act-pair · gemini-2.0-flash

    interesting

    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
    <bos>
    -1.00
     interesting
    -0.80
    interesting
    -0.74
     exciting
    -0.70
     troubling
    -0.68
    Interesting
    -0.67
     appealing
    -0.65
     frustrating
    -0.63
     fascinating
    -0.63
     disturbing
    -0.63
    POSITIVE LOGITS
    gonic
    0.72
    DotNetBar
    0.72
     defStyleAttr
    0.66
     snippetHide
    0.64
    UserScript
    0.63
    WithIdentifier
    0.61
    nEnter
    0.60
     bipartisan
    0.59
     Moha
    0.59
     /*#__
    0.58
    Activations Density 4.129%

    No Known Activations