© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5271
    Prev
    Next
    INDEX
    Explanations

    the words "Base" and "Inner", some code, and the word "sweet"

    oai_token-act-pair · gemini-2.0-flash

    Base

    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
     becauſe
    -0.81
    kloped
    -0.77
     itſelf
    -0.75
     ſche
    -0.68
     ſmall
    -0.68
     Theſe
    -0.68
     ―――――
    -0.63
    StructEnd
    -0.62
     faſt
    -0.62
     protoimpl
    -0.60
    POSITIVE LOGITS
    ymce
    0.68
     balanceOf
    0.65
    ngrx
    0.61
     priser
    0.61
     Solicitors
    0.60
    isissez
    0.59
     cerimonia
    0.59
    juana
    0.59
    wijl
    0.58
    IconModule
    0.58
    Activations Density 2.393%

    No Known Activations