© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11812
    Prev
    Next
    INDEX
    Explanations

    mentions of youth, age and time in general

    oai_token-act-pair · gemini-2.0-flash

    young

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    awtextra
    -0.73
    
    -0.67
     nonatomic
    -0.65
     متعلقه
    -0.63
    CollectionUtils
    -0.61
     MainAxisSize
    -0.60
    CommonModule
    -0.59
    
    -0.59
    WebElementEntity
    -0.58
     typelib
    -0.57
    POSITIVE LOGITS
     young
    2.09
    young
    1.65
    Young
    1.59
     YOUNG
    1.50
     Young
    1.48
     jeune
    1.48
    YOUNG
    1.32
     jonge
    1.30
     junge
    1.29
     jungen
    1.23
    Activations Density 4.919%

    No Known Activations