© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4568
    Prev
    Next
    INDEX
    Explanations

    content from sports reporting, particularly scores, teams, and standings

    oai_token-act-pair · gemini-2.0-flash

    Universities/Colleges

    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
     GenerationType
    -0.73
    
    -0.71
     خارجية
    -0.66
    makeConstraints
    -0.65
    RenderAtEndOf
    -0.64
     TestBed
    -0.64
    TemporalType
    -0.61
     dumbbells
    -0.60
     griega
    -0.60
     Isk
    -0.59
    POSITIVE LOGITS
     AssemblyTitle
    0.55
    setViewportView
    0.53
     Union
    0.44
    بات
    0.43
     doInBackground
    0.41
    Union
    0.40
     n
    0.40
    이션
    0.39
    arm
    0.39
     Sir
    0.38
    Activations Density 0.304%

    No Known Activations