© 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. 15833
    Prev
    Next
    INDEX
    Explanations

    words related to Unity project setup and version control

    oai_token-act-pair · gemini-2.0-flash

    Unity code

    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
    rungsseite
    -0.69
    permitAll
    -0.63
    LookAnd
    -0.55
    IVEREF
    -0.55
    bigr
    -0.54
    charpe
    -0.54
     HasFactory
    -0.54
    Enllaços
    -0.54
    Искәрмәләр
    -0.52
    hasMoreElements
    -0.52
    POSITIVE LOGITS
    Datuak
    0.52
    Offered
    0.51
     Avez
    0.49
     gani
    0.49
     hiel
    0.48
     Brewster
    0.47
    DllImport
    0.47
     patin
    0.45
     Apre
    0.45
    justed
    0.44
    Activations Density 1.052%

    No Known Activations