© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4343
    Prev
    Next
    INDEX
    Explanations

    negative sporting results around a club

    oai_token-act-pair · gemini-2.0-flash

    sports competition results

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    oquia
    -0.65
    destroyAll
    -0.59
    atorship
    -0.57
    érables
    -0.57
    ffilm
    -0.55
     radiation
    -0.54
    ruf
    -0.53
    omock
    -0.52
    OptionPane
    -0.51
    LookAnd
    -0.51
    POSITIVE LOGITS
    ServletException
    0.54
     חיצוניים
    0.52
     Pata
    0.47
    buku
    0.45
     vost
    0.45
    Collegamenti
    0.45
    belly
    0.44
    quiel
    0.44
    TextAppearance
    0.44
    Reprints
    0.43
    Activations Density 0.260%

    No Known Activations