© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11948
    Prev
    Next
    INDEX
    Explanations

    phrases that include negative contractions and terms related to sports teams and games

    oai_token-act-pair · gemini-2.0-flash

    Sports articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     bet
    -0.44
     encar
    -0.40
    <eos>
    -0.40
     wag
    -0.39
     अन
    -0.39
    ENCODING
    -0.38
     incar
    -0.37
    BET
    -0.37
     De
    -0.37
    提
    -0.36
    POSITIVE LOGITS
     فريبيس
    0.94
     Theſe
    0.84
     otomatig
    0.84
    principalTable
    0.77
     ModelExpression
    0.77
    Personensuche
    0.76
    GEBURTSDATUM
    0.75
     Majefty
    0.74
    TagMode
    0.73
    
    0.72
    Activations Density 0.194%

    No Known Activations