© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5490
    Prev
    Next
    INDEX
    Explanations

    words and word fragments that look like names or handles, including website addresses

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Билгалдахарш
    -0.63
    <bos>
    -0.62
     nakalista
    -0.61
    蛋
    -0.55
    Datuak
    -0.54
    ыгана
    -0.52
    atimes
    -0.51
    ις
    -0.50
    inda
    -0.49
    estacks
    -0.49
    POSITIVE LOGITS
     defaultstate
    0.68
    Tikang
    0.60
    closedir
    0.55
     TextInputType
    0.54
    zeczytaj
    0.53
    fazione
    0.53
     vė
    0.53
     Himo
    0.52
    Derp
    0.52
    herself
    0.52
    Activations Density 0.833%

    No Known Activations