© 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. 12716
    Prev
    Next
    INDEX
    Explanations

    URLs

    oai_token-act-pair · gemini-2.0-flash

    URLs or web addresses

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

    www

    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
    <bos>
    -0.57
    SpringRunner
    -0.56
    omiast
    -0.54
     Administrativna
    -0.49
    FileDescriptor
    -0.49
     dazu
    -0.49
    __.__
    -0.49
    elsif
    -0.49
    erals
    -0.49
    isRequired
    -0.48
    POSITIVE LOGITS
    SuppressMessage
    0.73
     pinulongan
    0.60
     فريبيس
    0.59
    ftagPool
    0.54
    tvguidetime
    0.53
    poli
    0.51
    IsMutable
    0.51
    Tazama
    0.50
     PackageManager
    0.50
     ✭✭
    0.49
    Activations Density 0.320%

    No Known Activations