© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12828
    Prev
    Next
    INDEX
    Explanations

    occurrences of "much", "many", or words related to quantity, preceeding other words

    oai_token-act-pair · gemini-2.0-flash

    quantity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    netbeans
    -0.53
    ⓧ
    -0.52
    LookAnd
    -0.52
    glMatrixMode
    -0.49
     ​​
    -0.49
     [
    -0.47
     deputies
    -0.46
     دیکھیے
    -0.46
    をよく
    -0.46
    andExpect
    -0.46
    POSITIVE LOGITS
    tvguidetime
    0.76
    addPreferredGap
    0.72
     étoient
    0.67
     ISNI
    0.63
     XCTest
    0.62
    Rhestr
    0.61
     avoient
    0.61
    ")));
    0.59
    úrate
    0.59
    ]='\
    0.58
    Activations Density 0.482%

    No Known Activations