© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4822
    Prev
    Next
    INDEX
    Explanations

    uses of prepositions, conjunctions, and pronouns to relate multiple entities

    oai_token-act-pair · gemini-2.0-flash

    proper nouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     ujednoznacz
    -0.88
    yntaxException
    -0.78
    migrationBuilder
    -0.77
    BagLayout
    -0.70
    BagConstraints
    -0.69
    complexContent
    -0.69
    UnsafeEnabled
    -0.69
    SPATH
    -0.68
     jScrollPane
    -0.68
     AttributeSet
    -0.67
    POSITIVE LOGITS
     Majefty
    0.56
    Your
    0.50
    Use
    0.50
    Color
    0.48
    Start
    0.48
    4
    0.47
    Values
    0.46
     pleaſure
    0.46
     greateſt
    0.46
    Source
    0.46
    Activations Density 43.095%

    No Known Activations