© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2353
    Prev
    Next
    INDEX
    Explanations

    the articles "a", "an", and "the"

    oai_token-act-pair · gemini-2.0-flash

    informal titles or descriptors

    np_token-act-pair-logits · gpt-4o-mini

    The

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Parcelize
    -0.58
     vejo
    -0.57
     my
    -0.57
     maux
    -0.55
     tôi
    -0.55
     économiques
    -0.53
    rotnie
    -0.52
     comigo
    -0.50
     motivadoras
    -0.50
     we
    -0.49
    POSITIVE LOGITS
    ValueStyle
    0.73
    RenderAtEndOf
    0.69
     guy
    0.65
     fact
    0.64
    JspWriter
    0.59
     ivelany
    0.57
     funniest
    0.57
     fellow
    0.56
     lady
    0.56
     dude
    0.56
    Activations Density 4.011%

    No Known Activations