© 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. 10196
    Prev
    Next
    INDEX
    Explanations

    German text with modal verbs (kann, muss, soll, etc).

    oai_token-act-pair · gemini-2.0-flash

    tokens related to programming or technical terms

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

    German or code fragments

    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
    FLICT
    -0.52
    Américaine
    -0.51
     lo
    -0.51
     Through
    -0.51
    Atsauces
    -0.50
    ngdoc
    -0.50
    Lähteet
    -0.50
     
    -0.49
    Kapcsolódó
    -0.49
    belt
    -0.48
    POSITIVE LOGITS
    ISupport
    0.57
     InputDecoration
    0.57
    WriteBarrier
    0.54
    [++
    0.52
    出版年
    0.52
    mybatisplus
    0.52
     AssemblyProduct
    0.51
     referenties
    0.51
     virš
    0.50
    الحياه
    0.50
    Activations Density 0.353%

    No Known Activations