© 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. 8238
    Prev
    Next
    INDEX
    Explanations

    content from or relating to online forums

    oai_token-act-pair · gemini-2.0-flash

    code or programming syntax elements

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

    Website comments

    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
    findpost
    -0.59
     conosco
    -0.49
    bootstrapcdn
    -0.46
     saites
    -0.45
    urcht
    -0.44
     Elasticsearch
    -0.44
    Ass
    -0.43
     tutup
    -0.42
     Soviets
    -0.42
     CountDown
    -0.42
    POSITIVE LOGITS
     "..\..\..\
    0.69
     "..\..\
    0.66
    yntaxException
    0.65
    nady
    0.62
     externi
    0.61
    Aiheesta
    0.60
    GraphicsUnit
    0.59
    قایناقلار
    0.56
    __":
    0.56
     initComponents
    0.55
    Activations Density 4.033%

    No Known Activations