© 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. 5060
    Prev
    Next
    INDEX
    Explanations

    the word "went" or "going" often alongside the word "with."

    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
    go
    -0.53
     Go
    -0.53
     go
    -0.51
    Go
    -0.51
    ut
    -0.42
     riuscito
    -0.39
     Rounded
    -0.39
     ulang
    -0.39
     языке
    -0.39
     Concerning
    -0.38
    POSITIVE LOGITS
    Autoritní
    0.89
    GEBURTSDATUM
    0.80
     gynhyrchwyd
    0.75
     saites
    0.73
    rungsseite
    0.72
    IBarButtonItem
    0.72
    IntoConstraints
    0.71
     }{@
    0.70
    ]")]
    0.70
    ReusableCell
    0.69
    Activations Density 0.434%

    No Known Activations