© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9548
    Prev
    Next
    INDEX
    Explanations

    product model numbers

    oai_token-act-pair · gemini-2.0-flash

    technical terms and product models

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

    technical specifications

    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
     referenties
    -0.57
    IsMutable
    -0.51
    ätzlich
    -0.49
    Sortie
    -0.49
    AddHtmlAttribute
    -0.49
     bet
    -0.48
     >=",
    -0.47
    Rujukan
    -0.47
    Արտաքին
    -0.46
    Enllaços
    -0.46
    POSITIVE LOGITS
     تضيفلها
    0.53
     Vás
    0.49
     /*#__
    0.47
    
    0.47
    __()
    0.47
    struzione
    0.46
    multer
    0.46
     pfalz
    0.46
     Verkä
    0.46
    SuppressLint
    0.45
    Activations Density 5.182%

    No Known Activations