© 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. 6430
    Prev
    Next
    INDEX
    Explanations

    Japanese text and programming code

    oai_token-act-pair · gemini-2.0-flash

    code and libraries

    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
    pragma
    -0.63
    lapsingToolbar
    -0.59
     IOError
    -0.59
     manqué
    -0.56
    gelöst
    -0.55
     škoda
    -0.53
    ubio
    -0.52
     OnTriggerEnter
    -0.52
     should
    -0.51
    antia
    -0.51
    POSITIVE LOGITS
    Personensuche
    0.61
    Portale
    0.59
     Exacts
    0.58
     externi
    0.52
    VIAF
    0.49
    ernacle
    0.48
    енча
    0.48
    новништво
    0.47
    inander
    0.47
    InjectAttribute
    0.47
    Activations Density 0.359%

    No Known Activations