© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3456
    Prev
    Next
    INDEX
    Explanations

    the word "late" and related historical and current events

    oai_token-act-pair · gemini-2.0-flash

    time related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    IVEREF
    -0.51
    PropertyChanging
    -0.50
    })]
    -0.49
     beginnetje
    -0.46
    liğini
    -0.44
    quette
    -0.44
    AntiForgeryToken
    -0.42
     testGet
    -0.39
    Референце
    -0.38
    garis
    -0.38
    POSITIVE LOGITS
     later
    1.80
     late
    1.60
    later
    1.58
    Later
    1.53
     afterwards
    1.53
     afterward
    1.46
     LATER
    1.45
     Later
    1.43
     AFTER
    1.36
     LATE
    1.34
    Activations Density 2.823%

    No Known Activations