© 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. 5378
    Prev
    Next
    INDEX
    Explanations

    words related to scientific properties and characteristics

    oai_token-act-pair · gemini-2.0-flash

    Properties and characteristics

    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
    Characteristics
    -0.85
     Characteristics
    -0.83
     characteristics
    -0.79
    Vorteile
    -0.79
    characteristics
    -0.78
     ivelany
    -0.77
     Attributes
    -0.75
    PerformLayout
    -0.74
    Factors
    -0.73
     Factors
    -0.72
    POSITIVE LOGITS
    Portale
    0.54
     træ
    0.44
     urma
    0.42
    caris
    0.40
    Portail
    0.39
    <h1>
    0.39
    存于互联网档案馆
    0.39
    car
    0.39
     Público
    0.39
     Económica
    0.38
    Activations Density 1.682%

    No Known Activations