© 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. 3553
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers

    oai_token-act-pair · gemini-2.0-flash

    names or words with varying formats

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

    Math and programming posts

    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
    -0.85
    uxxxx
    -0.83
     AssemblyCompany
    -0.82
    ⓧ
    -0.82
    OGND
    -0.77
     Préférences
    -0.74
     متعلقه
    -0.73
     AssemblyTitle
    -0.73
    awaiter
    -0.73
    الإنجليزية
    -0.72
    POSITIVE LOGITS
    Nye
    0.44
     desta
    0.42
     deste
    0.41
    sop
    0.38
    alive
    0.38
     Nye
    0.38
    ң
    0.37
     automatiques
    0.37
    ่าน
    0.36
     väl
    0.36
    Activations Density 4.707%

    No Known Activations