© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13209
    Prev
    Next
    INDEX
    Explanations

    instances of people receiving appointments, promotions, awards, or honors

    oai_token-act-pair · gemini-2.0-flash

    Awards and honors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ThroughAttribute
    -0.75
    BindingResult
    -0.67
    MLLoader
    -0.67
     NUKAT
    -0.66
    ResumeLayout
    -0.63
    initializeApp
    -0.61
     AppDelegate
    -0.61
    AccessorTable
    -0.60
    CloseOperation
    -0.60
    исленность
    -0.59
    POSITIVE LOGITS
    pahan
    0.46
    copus
    0.45
    ISTICS
    0.45
    LANTA
    0.44
     esquecer
    0.44
    hooter
    0.42
    řevě
    0.42
    ship
    0.41
    はじめに
    0.40
    >())
    0.40
    Activations Density 0.549%

    No Known Activations