© 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. 9455
    Prev
    Next
    INDEX
    Explanations

    the phrase "All-Star", "All-Time" or "All-Century"

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating 'All Century' or 'All Time' references

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

    sports team recognition

    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
     oka
    -0.56
    nelli
    -0.56
    Datuak
    -0.52
     mend
    -0.48
     通販
    -0.47
    gants
    -0.46
    BindingSource
    -0.45
    elis
    -0.45
     kaynağından
    -0.44
     separate
    -0.44
    POSITIVE LOGITS
     torchvision
    0.64
    EndContext
    0.62
    cèse
    0.59
    MergeFrom
    0.57
    aarrggbb
    0.57
    Polizei
    0.54
    FTFY
    0.54
    ValueStyle
    0.54
    windowFixed
    0.53
    BuilderFactory
    0.53
    Activations Density 0.110%

    No Known Activations