© 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. 5663
    Prev
    Next
    INDEX
    Explanations

    street addresses and locations, especially in Liverpool

    oai_token-act-pair · gemini-2.0-flash

    genes and legal jargon

    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
    expandindo
    -0.58
     MainAxisSize
    -0.56
     defaultstate
    -0.55
    embolso
    -0.55
    WithMany
    -0.55
    })*/
    -0.51
    modb
    -0.50
    mybatisplus
    -0.49
     CURIAM
    -0.48
     COE
    -0.46
    POSITIVE LOGITS
    AndEndTag
    0.64
     Nuss
    0.60
     Reſ
    0.55
     Theſe
    0.55
     pngtree
    0.53
     himſelf
    0.52
     uppdater
    0.52
     Ilustra
    0.51
     uſ
    0.51
     Beſ
    0.50
    Activations Density 1.670%

    No Known Activations