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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10593
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs like forms of "to be", "to have", and modal verbs, often in conjunction with words indicating planning or obligation.

    oai_token-act-pair · gemini-2.0-flash

    Clauses starting with gerunds

    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
    MigrationBuilder
    -0.47
    ﴾
    -0.42
    ugier
    -0.39
    ...”
    -0.39
    <h4>
    -0.38
     ---
    -0.38
    ,’”
    -0.36
    ...
    -0.36
     للاسماء
    -0.35
     JTextArea
    -0.35
    POSITIVE LOGITS
     your
    0.88
    MemoryWarning
    0.84
    ItemBackground
    0.75
     my
    0.75
    WriteTagHelper
    0.73
    brainly
    0.72
    SourceChecksum
    0.71
    Geplaatst
    0.71
     MainAxisSize
    0.69
     архивлан
    0.69
    Activations Density 17.324%

    No Known Activations