© 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. 4734
    Prev
    Next
    INDEX
    Explanations

    mentions of scientific study designs and the names of popular singing competitions

    oai_token-act-pair · gemini-2.0-flash

    Clinical trials

    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
    enderror
    -0.63
    oredCriteria
    -0.62
    webElementGuid
    -0.60
    ьаж
    -0.59
    TypedDataSet
    -0.59
     Chwiliwch
    -0.58
    انتهای
    -0.57
    OGND
    -0.54
    transQ
    -0.53
    וויק
    -0.52
    POSITIVE LOGITS
    IntoConstraints
    0.65
     Au
    0.63
     consultato
    0.61
    RemoteException
    0.55
    Au
    0.53
     mon
    0.51
     TAMBÉM
    0.49
    +#+
    0.49
     double
    0.48
    moveToFirst
    0.48
    Activations Density 2.055%

    No Known Activations