© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4428
    Prev
    Next
    INDEX
    Explanations

    phone numbers

    oai_token-act-pair · gemini-2.0-flash

    segments featuring a mix of numbers and specific words

    np_token-act-pair-logits · gpt-4o-mini

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    httphttps
    -0.69
    ⓘ
    -0.69
    numerusform
    -0.69
    apimachinery
    -0.67
    AutoField
    -0.67
    InjectAttribute
    -0.65
     kaarangay
    -0.65
    uxxxx
    -0.63
    yntaxException
    -0.63
    enderror
    -0.63
    POSITIVE LOGITS
    plass
    0.47
     descrição
    0.46
    rimin
    0.45
    utzen
    0.45
     gun
    0.43
    gående
    0.42
     alluminio
    0.42
     vzor
    0.42
     kirim
    0.41
     jäsen
    0.41
    Activations Density 0.441%

    No Known Activations