© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10431
    Prev
    Next
    INDEX
    Explanations

    mentions of age, especially numerical ages or phrases including the word "old".

    oai_token-act-pair · gemini-2.0-flash

    the word "old"

    np_token-act-pair-logits · gpt-4o-mini

    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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     kaynağından
    -0.75
     Geraadpleegd
    -0.60
     HasFactory
    -0.52
     Italijanski
    -0.52
    orteur
    -0.52
     Италијани
    -0.52
    Datuak
    -0.50
    obacz
    -0.50
    альных
    -0.48
    INSEE
    -0.48
    POSITIVE LOGITS
     old
    3.09
    old
    2.55
    Old
    2.20
     OLD
    2.14
     viejo
    2.11
     Old
    2.09
    OLD
    2.03
     vieille
    2.03
     vecchio
    2.02
     viejos
    1.98
    Activations Density 2.532%

    No Known Activations