© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12590
    Prev
    Next
    INDEX
    Explanations

    the words "minute", "save", "saving", and "saved"

    oai_token-act-pair · gemini-2.0-flash

    minute or save

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    thâu
    -0.77
     ―――――
    -0.76
     pinulongan
    -0.76
     AssemblyCulture
    -0.73
    tieth
    -0.72
    UnknownFields
    -0.70
    })*/
    -0.70
     iſt
    -0.70
    haustible
    -0.70
    psack
    -0.69
    POSITIVE LOGITS
    ,
    0.57
    ;
    0.50
     &
    0.49
    手で
    0.49
    ↵
    0.48
     definitively
    0.47
     typically
    0.46
     hoj
    0.46
     once
    0.46
    SaveChangesAsync
    0.46
    Activations Density 1.908%

    No Known Activations