© 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. 3474
    Prev
    Next
    INDEX
    Explanations

    initials separated by periods and action verbs

    oai_token-act-pair · gemini-2.0-flash

    academic/research texts

    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
    <eos>
    -1.55
    ParallelGroup
    -0.71
     […]
    -0.63
    ↵↵
    -0.60
    <unused63>
    -0.58
    ⓧ
    -0.58
    <unused61>
    -0.58
    printStackTrace
    -0.56
    gt
    -0.55
     ***!
    -0.54
    POSITIVE LOGITS
     itſelf
    0.83
     présidenti
    0.79
     ویکی‌پدیای
    0.77
     enfans
    0.77
     medesimo
    0.73
     stället
    0.71
    .
    0.69
    brainly
    0.68
     juridiques
    0.67
     ainfi
    0.66
    Activations Density 22.918%

    No Known Activations