© 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. 16379
    Prev
    Next
    INDEX
    Explanations

    symbols and strings common in computer code

    oai_token-act-pair · gemini-2.0-flash

    code and scientific data

    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
     “
    -0.51
     …
    -0.44
     ...
    -0.43
     "
    -0.43
     base
    -0.42
     et
    -0.41
     El
    -0.40
    opla
    -0.40
     qu
    -0.40
     Pe
    -0.40
    POSITIVE LOGITS
     المعيارى
    0.98
     Theſe
    0.90
     Monfieur
    0.89
     étoit
    0.88
     feroit
    0.88
     auroit
    0.84
    audiovisuel
    0.82
     auffi
    0.81
    CloseOperation
    0.81
     étoient
    0.81
    Activations Density 16.411%

    No Known Activations