© 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. 12569
    Prev
    Next
    INDEX
    Explanations

    words that are used in academic papers on cosmology to relate different concepts

    oai_token-act-pair · gemini-2.0-flash

    Physics

    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
    בודה
    -0.58
    вік
    -0.54
    ErrUnexpectedEOF
    -0.46
     NDL
    -0.44
    StackNavigator
    -0.43
     vernis
    -0.43
     functie
    -0.42
     specchio
    -0.41
    ėtų
    -0.41
     platt
    -0.41
    POSITIVE LOGITS
    osoba
    0.71
    __':
    0.67
     دیکھیے
    0.66
    styleable
    0.66
    __":
    0.63
     муніципалі
    0.60
    MessageInfo
    0.60
     lenker
    0.56
    ftagPool
    0.56
     Oy
    0.55
    Activations Density 4.526%

    No Known Activations