© 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. 4017
    Prev
    Next
    INDEX
    Explanations

    information about people like family, location, and names

    oai_token-act-pair · gemini-2.0-flash

    biography texts

    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
    WindowConstants
    -0.63
    endpush
    -0.55
    Joey
    -0.53
     nagu
    -0.49
    Kaieteur
    -0.49
    ázquez
    -0.49
     Cu
    -0.47
    Malley
    -0.46
    ősz
    -0.46
     Joey
    -0.45
    POSITIVE LOGITS
    addCriterion
    0.69
    oredCriteria
    0.65
     springfox
    0.60
     Ezra
    0.60
     porté
    0.56
    thenia
    0.56
     Eunice
    0.54
    httphttps
    0.53
    kura
    0.52
     Gli
    0.51
    Activations Density 1.273%

    No Known Activations