© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1599
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating cause and effect, or relationship

    oai_token-act-pair · gemini-2.0-flash

    to

    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
     debido
    -0.70
     ujednoznacz
    -0.70
     devido
    -0.69
    tvguidetime
    -0.66
     dû
    -0.59
     due
    -0.59
    pable
    -0.58
     inherits
    -0.52
     aufgrund
    -0.51
     Debido
    -0.51
    POSITIVE LOGITS
    ruptedException
    0.73
    ISupport
    0.60
    AutoField
    0.59
    abstractmethod
    0.58
    CodeAttribute
    0.54
    awaiter
    0.54
    Portale
    0.54
    ="#">
    0.53
    HasAnnotation
    0.53
    UnusedPrivate
    0.52
    Activations Density 10.563%

    No Known Activations