© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6095
    Prev
    Next
    INDEX
    Explanations

    the word "serial."

    oai_token-act-pair · gemini-2.0-flash

    serial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    simus
    -0.58
     plans
    -0.58
    جغرافيا
    -0.57
    ricane
    -0.56
     COVID
    -0.56
     large
    -0.54
    SerializeField
    -0.54
     everything
    -0.53
    mense
    -0.53
    cuits
    -0.53
    POSITIVE LOGITS
    )')
    0.81
     ***/
    0.81
    ']],
    0.81
     aveug
    0.80
     />";
    0.80
     Normdatei
    0.77
     mourut
    0.77
    \}}
    0.77
    ?")
    0.77
    )")
    0.77
    Activations Density 1.860%

    No Known Activations