© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5016
    Prev
    Next
    INDEX
    Explanations

    mentions of professional accomplishments, awards, or formal titles

    oai_token-act-pair · gemini-2.0-flash

    News and business articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    mockito
    -0.50
    Erfolge
    -0.48
     oot
    -0.46
    cshtml
    -0.46
    /><
    -0.45
     cou
    -0.44
    Thunk
    -0.44
    iento
    -0.44
    "]["
    -0.44
    Portale
    -0.44
    POSITIVE LOGITS
     PublicKey
    0.61
     disambiguazione
    0.61
     ProtoMessage
    0.59
    Šaltiniai
    0.59
    Produzione
    0.58
     autorytatywna
    0.58
    expandindo
    0.58
    ($__
    0.56
     للاسماء
    0.56
    inc
    0.55
    Activations Density 0.439%

    No Known Activations