© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5143
    Prev
    Next
    INDEX
    Explanations

    phrases discussing aging and appearance

    oai_token-act-pair · 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
    zugehen
    -0.44
    findpost
    -0.44
    tal
    -0.42
     nyt
    -0.42
     mö
    -0.40
     jadx
    -0.40
     Hause
    -0.40
     Coat
    -0.39
     om
    -0.39
     der
    -0.39
    POSITIVE LOGITS
    enderror
    0.77
     متعلقه
    0.71
    PerformLayout
    0.69
     Huffman
    0.67
     laugh
    0.66
    __*/
    0.66
     gynhyrchwyd
    0.66
     itſelf
    0.66
    DataContract
    0.65
    ollectionView
    0.63
    Activations Density 0.841%

    No Known Activations