© 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. 3973
    Prev
    Next
    INDEX
    Explanations

    words related to email and online communication

    oai_token-act-pair · gemini-2.0-flash

    tokens related to email

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

    email

    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
     florales
    -0.57
     descal
    -0.52
    iget
    -0.51
    Ầ
    -0.50
    󠁣
    -0.49
    fisk
    -0.48
    Nationalité
    -0.47
     fero
    -0.47
     ويكيميديا
    -0.46
     bParam
    -0.46
    POSITIVE LOGITS
    +#+#
    0.81
    HasForeignKey
    0.61
     становника
    0.57
    TagMode
    0.57
    ::_('
    0.56
    WithIOException
    0.52
    ジアム
    0.52
    RepeatedField
    0.52
    かわらず
    0.50
    omock
    0.49
    Activations Density 1.588%

    No Known Activations