© 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. 11939
    Prev
    Next
    INDEX
    Explanations

    the beginning of the word "squirt" or a word starting with "squ"

    oai_token-act-pair · gemini-2.0-flash

    squ

    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
     Réponses
    -0.65
    ValueStyle
    -0.62
     onCreateView
    -0.58
    oredCriteria
    -0.57
     Numerade
    -0.55
    noun
    -0.52
    UnsafeEnabled
    -0.52
    ReusableCell
    -0.52
    migrationBuilder
    -0.50
     noun
    -0.50
    POSITIVE LOGITS
    Lähteet
    0.57
     Compagn
    0.52
     AW
    0.51
    AsUp
    0.50
    ůměr
    0.49
    marginHorizontal
    0.49
    marginVertical
    0.48
    Pautan
    0.48
    ագրություններ
    0.47
    ี่ยน
    0.46
    Activations Density 0.358%

    No Known Activations