© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3786
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to old age and aging

    oai_token-act-pair · gemini-2.0-flash

    old

    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
    intios
    -0.73
     المعيارى
    -0.72
     Италијани
    -0.70
     referenties
    -0.69
     متعلقه
    -0.68
    évaluateur
    -0.68
    providedIn
    -0.66
    awtextra
    -0.65
    AndroidJUnit
    -0.64
    WebElementEntity
    -0.63
    POSITIVE LOGITS
     old
    3.22
    old
    2.59
    Old
    2.33
     Old
    2.25
     OLD
    2.19
    OLD
    2.11
     viejo
    1.96
     oude
    1.83
     vieux
    1.83
     viejos
    1.79
    Activations Density 3.512%

    No Known Activations