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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10855
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and symbols and the words "rate", "fecund", and "selection"

    oai_token-act-pair · gemini-2.0-flash

    Equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    endpush
    -0.80
    expandindo
    -0.77
    oa̍t
    -0.71
     rêver
    -0.69
    Rhestr
    -0.68
     tombé
    -0.67
    ConstraintMaker
    -0.66
    lccn
    -0.66
    \{\\
    -0.66
     allAfrica
    -0.65
    POSITIVE LOGITS
     direction
    0.47
    ◄
    0.46
     Référence
    0.46
    المكان
    0.44
     le
    0.43
     well
    0.42
    BeforeMethod
    0.42
     brought
    0.40
    Pointer
    0.40
    direction
    0.40
    Activations Density 0.748%

    No Known Activations