© 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. 11723
    Prev
    Next
    INDEX
    Explanations

    python identifiers with leading underscores, often associated with class methods

    oai_token-act-pair · gemini-2.0-flash

    __

    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
    ::$_
    -0.79
     doInBackground
    -0.68
    ClientSize
    -0.63
    تقاوى
    -0.63
    BeginContext
    -0.59
    TestingModule
    -0.53
     correctes
    -0.52
    aarrggbb
    -0.52
    IVEREF
    -0.52
    GOTREF
    -0.50
    POSITIVE LOGITS
    Portale
    0.60
     piedi
    0.54
    strual
    0.50
     Dray
    0.49
     Harz
    0.49
    Demografia
    0.49
    rigin
    0.49
    iastical
    0.49
    gines
    0.48
    casila
    0.48
    Activations Density 0.308%

    No Known Activations