© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5462
    Prev
    Next
    INDEX
    Explanations

    instances where items are displayed within a legal or artistic context

    oai_token-act-pair · gemini-2.0-flash

    Consideration or presentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Phew
    -0.56
     Fre
    -0.56
    HasOne
    -0.55
    setTypeface
    -0.54
    τρα
    -0.53
     Gal
    -0.50
    Spoljašnje
    -0.50
    ISupport
    -0.49
    ristan
    -0.49
     Power
    -0.49
    POSITIVE LOGITS
    WriteBarrier
    0.76
     Monfieur
    0.69
    <bos>
    0.68
    ///</
    0.66
    uxxxx
    0.62
    ChildScrollView
    0.58
     EconPapers
    0.56
    ----</
    0.56
     espagne
    0.55
     Wiktionnaire
    0.55
    Activations Density 5.858%

    No Known Activations