© 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. 7367
    Prev
    Next
    INDEX
    Explanations

    information about football players and their positions such as left back

    oai_token-act-pair · gemini-2.0-flash

    terms related to football positions or roles

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

    soccer

    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
    __':
    -0.61
    AsUp
    -0.60
     الرياضيه
    -0.59
    Према
    -0.59
     forwards
    -0.57
    >-->
    -0.56
    __':
    -0.56
    __":
    -0.56
    inheritDoc
    -0.52
     BoxFit
    -0.52
    POSITIVE LOGITS
    Personensuche
    0.65
     متعلقه
    0.65
    Marshaller
    0.60
    minecraftforge
    0.53
     Embaj
    0.51
    부터
    0.49
     jár
    0.49
    ScopeManager
    0.49
     correctes
    0.49
     Roskov
    0.48
    Activations Density 0.448%

    No Known Activations