© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13969
    Prev
    Next
    INDEX
    Explanations

    words relating to conflict and victory/defeat.

    oai_token-act-pair · gemini-2.0-flash

    winning or losing

    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
     win
    -0.63
     AssemblyTitle
    -0.57
     memenangkan
    -0.53
     wins
    -0.52
    awin
    -0.51
     victory
    -0.51
     control
    -0.49
     winning
    -0.48
    akse
    -0.48
     preference
    -0.48
    POSITIVE LOGITS
    basicConfig
    0.63
    EDEFAULT
    0.63
    IVEREF
    0.59
     الرياضيه
    0.58
     getopt
    0.54
    golang
    0.53
    enumii
    0.52
    udah
    0.51
    
    0.50
    enumi
    0.50
    Activations Density 1.498%

    No Known Activations