© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10914
    Prev
    Next
    INDEX
    Explanations

    words that describe physical contact and/or consequences of an action

    oai_token-act-pair · gemini-2.0-flash

    descriptions of events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Houſe
    -1.08
     myſelf
    -1.03
     Wikispecies
    -0.94
    ^(@)
    -0.93
     ་་
    -0.90
     houſe
    -0.88
     pleaſure
    -0.88
     iſt
    -0.87
     Majefty
    -0.86
     poffible
    -0.86
    POSITIVE LOGITS
     his
    0.73
     their
    0.58
     my
    0.58
    my
    0.54
     your
    0.54
    his
    0.53
    al
    0.47
     her
    0.47
    ed
    0.46
    im
    0.43
    Activations Density 8.458%

    No Known Activations