© 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
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14078
    Prev
    Next
    INDEX
    Explanations

    long alphanumeric strings including square roots and other symbols often found in complex equations.

    oai_token-act-pair · gemini-2.0-flash

    Numbers

    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
    mployment
    -0.61
    blings
    -0.60
    ](#
    -0.58
     initComponents
    -0.57
    Manbalar
    -0.56
    CROSSTALK
    -0.55
     insuffisamment
    -0.55
    bkz
    -0.54
    PerformLayout
    -0.53
     "../../../
    -0.53
    POSITIVE LOGITS
    modelBuilder
    0.67
    tagHelperRunner
    0.65
     Blatt
    0.62
     kasarigan
    0.61
    المناصب
    0.58
     Arden
    0.55
    SpringBootTest
    0.54
     Cologne
    0.53
     Alderman
    0.53
     prer
    0.53
    Activations Density 2.279%

    No Known Activations