© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4092
    Prev
    Next
    INDEX
    Explanations

    mentions of competitions, especially sporting competitions

    oai_token-act-pair · gemini-2.0-flash

    tournament

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Photocase
    -0.71
     OnInit
    -0.66
    Qaeda
    -0.66
     Qaeda
    -0.66
    ẨM
    -0.66
     Janeiro
    -0.65
    anskrit
    -0.65
     defaultstate
    -0.64
     Anglia
    -0.64
    akesh
    -0.63
    POSITIVE LOGITS
     Efq
    0.71
    stays
    0.66
     avoient
    0.66
     Monfieur
    0.65
     ſtate
    0.65
     Jefus
    0.63
     whoſe
    0.61
    jména
    0.60
     affez
    0.59
     pleaſure
    0.59
    Activations Density 0.851%

    No Known Activations