© 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. 14247
    Prev
    Next
    INDEX
    Explanations

    descriptions of sports game outcomes, especially when wins, losses, goals, or injuries are mentioned

    oai_token-act-pair · gemini-2.0-flash

    programming and technology terms

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

    winning

    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
    TargetException
    -0.75
    PerformLayout
    -0.69
     cdti
    -0.68
    webElementXpaths
    -0.66
     Majefty
    -0.65
    protoimpl
    -0.65
     Lordships
    -0.64
     doubtnut
    -0.63
     itſelf
    -0.61
    évaluateur
    -0.60
    POSITIVE LOGITS
    NgModule
    0.58
     над
    0.53
     over
    0.48
    bouncycastle
    0.46
     NgModule
    0.45
     acc
    0.44
     per
    0.44
     con
    0.44
     meng
    0.43
    Sure
    0.43
    Activations Density 0.826%

    No Known Activations