© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10354
    Prev
    Next
    INDEX
    Explanations

    PHP code syntax and array operations, including assignments, function definitions, and array manipulations.

    oai_token-act-pair · gemini-2.0-flash

    Equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ברי
    -0.49
    министра
    -0.49
     r
    -0.47
    صاص
    -0.47
     l
    -0.46
    قایناقلار
    -0.46
    roller
    -0.45
     self
    -0.45
     nâu
    -0.45
    reggio
    -0.44
    POSITIVE LOGITS
    ScopeManager
    0.79
     Cæsar
    0.71
    LookAnd
    0.71
     Cister
    0.70
    |}{$
    0.70
     Exacts
    0.69
     metamorphic
    0.69
     fathoms
    0.69
     Kilkenny
    0.68
    CodeDom
    0.68
    Activations Density 1.156%

    No Known Activations