© 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. 3223
    Prev
    Next
    INDEX
    Explanations

    mentions of rugby and Irish places and people

    oai_token-act-pair · gemini-2.0-flash

    terms related to sports events or achievements

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

    Sports articles

    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
    expandindo
    -0.72
    __((
    -0.69
    EndInit
    -0.69
     zvuky
    -0.60
    ]--;
    -0.59
     Fußball
    -0.58
     Football
    -0.58
    AnimationsModule
    -0.58
    ManagedBean
    -0.57
     Buried
    -0.57
    POSITIVE LOGITS
    StructEnd
    0.54
     Gesta
    0.49
    performance
    0.47
    ########.
    0.46
     ProtoMessage
    0.46
    setattr
    0.46
    uitton
    0.45
     Agust
    0.45
    protoimpl
    0.44
    Bronnen
    0.44
    Activations Density 1.047%

    No Known Activations