© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9865
    Prev
    Next
    INDEX
    Explanations

    the word "are".

    oai_token-act-pair · gemini-2.0-flash

    are

    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
    ,
    -0.49
     caen
    -0.47
    .
    -0.46
    /
    -0.45
     As
    -0.45
    >
    -0.45
    tl
    -0.44
    ppus
    -0.44
    ↵
    -0.44
    ">
    -0.43
    POSITIVE LOGITS
    <bos>
    1.89
    хьтан
    1.22
    AccessorTable
    1.15
    awtextra
    1.15
    tagHelperRunner
    1.15
    GEBURTSDATUM
    1.13
    MLLoader
    1.13
     propOrder
    1.12
    LookAnd
    1.10
     invokingState
    1.09
    Activations Density 0.317%

    No Known Activations