© 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. 12649
    Prev
    Next
    INDEX
    Explanations

    the words "email" and "interface"

    oai_token-act-pair · gemini-2.0-flash

    mail

    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
     RISERV
    -0.70
     dentaire
    -0.69
    ########.
    -0.67
     Transfermarkt
    -0.63
    tabilidad
    -0.62
     autorytatywna
    -0.62
    expandindo
    -0.61
    tserrat
    -0.61
     auroit
    -0.60
    )";
    -0.60
    POSITIVE LOGITS
    rungsseite
    0.66
    ↵↵
    0.56
     betweenstory
    0.54
     boli
    0.54
    RTDA
    0.52
    ↵
    0.52
    DebuggerNonUser
    0.51
    .
    0.50
     molest
    0.50
    BeginContext
    0.47
    Activations Density 0.262%

    No Known Activations