© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10566
    Prev
    Next
    INDEX
    Explanations

    date-like numbers and other sports and TV statistics

    oai_token-act-pair · gemini-2.0-flash

    9

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     resourceCulture
    -0.62
     van
    -0.56
    تقاوى
    -0.56
     her
    -0.55
     he
    -0.54
     c
    -0.54
     che
    -0.52
    UserScript
    -0.52
     crossorigin
    -0.52
     Lo
    -0.51
    POSITIVE LOGITS
     ſtate
    0.65
     itſelf
    0.65
     Hift
    0.64
     ZAP
    0.62
     preſent
    0.61
     purpoſe
    0.59
     UPM
    0.59
     inſ
    0.59
     Moors
    0.58
     fubject
    0.58
    Activations Density 0.284%

    No Known Activations