© 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. 1568
    Prev
    Next
    INDEX
    Explanations

    past-tense verbs, frequently those used in legal or scientific writing

    oai_token-act-pair · gemini-2.0-flash

    Words ending in "ed"

    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
     BoxDecoration
    -0.59
     plena
    -0.42
    worn
    -0.40
     paznok
    -0.40
    ician
    -0.39
     Worn
    -0.38
     opérés
    -0.38
    UDI
    -0.38
    Aire
    -0.38
     bien
    -0.38
    POSITIVE LOGITS
    <bos>
    1.34
     went
    0.78
    matchCondition
    0.75
     AssemblyTitle
    0.73
    threw
    0.72
     gave
    0.71
     flew
    0.70
     threw
    0.70
     mourut
    0.68
     took
    0.66
    Activations Density 1.285%

    No Known Activations