© 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. 3887
    Prev
    Next
    INDEX
    Explanations

    words indicating location and surrounding context

    oai_token-act-pair · gemini-2.0-flash

    Locations and areas

    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
     fraî
    -0.46
     possano
    -0.46
     namorados
    -0.46
     culturelles
    -0.46
     históricos
    -0.45
     letteratura
    -0.44
     domingos
    -0.44
     român
    -0.44
     femininas
    -0.44
     storica
    -0.43
    POSITIVE LOGITS
     >=",
    0.88
    weiterlesen
    0.73
     mines
    0.70
     mine
    0.69
     bridge
    0.69
    ➟
    0.69
    Autoritní
    0.68
     map
    0.68
    argest
    0.67
    Redaktion
    0.66
    Activations Density 4.192%

    No Known Activations