© 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. 9570
    Prev
    Next
    INDEX
    Explanations

    connections between sports teams, coaches, and locations

    oai_token-act-pair · gemini-2.0-flash

    technical jargon or specialized terms

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

    Sports coaches and managers

    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
     ***!
    -0.79
    AntiForgeryToken
    -0.66
     "..\..\
    -0.65
     ModelExpression
    -0.62
     "..\..\..\
    -0.58
     nakalista
    -0.56
    nestjs
    -0.55
    Véxase
    -0.52
     BoxFit
    -0.52
    Receive
    -0.52
    POSITIVE LOGITS
    NOPQRST
    0.66
    uyasha
    0.57
    BagConstraints
    0.55
    queous
    0.51
    celotti
    0.51
     primaire
    0.49
    solete
    0.48
     CBT
    0.47
     falleció
    0.47
     Chord
    0.46
    Activations Density 0.632%

    No Known Activations