© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3605
    Prev
    Next
    INDEX
    Explanations

    words that describe things you would find in a house

    oai_token-act-pair · gemini-2.0-flash

    equipment/machine operation

    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
     للاسماء
    -0.59
     doInBackground
    -0.55
    requestCode
    -0.55
    libft
    -0.52
    paravant
    -0.52
    pic
    -0.50
    CPtr
    -0.50
    ToAction
    -0.49
    Vanjske
    -0.48
     مخطط
    -0.47
    POSITIVE LOGITS
     doors
    0.69
     door
    0.64
     Doors
    0.60
     glass
    0.60
     estekak
    0.58
    jsonwebtoken
    0.57
    QMetaType
    0.57
    Doors
    0.55
     Door
    0.54
     wire
    0.54
    Activations Density 2.878%

    No Known Activations