© 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. 1672
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "last" or other words implying the end of something

    oai_token-act-pair · gemini-2.0-flash

    ere

    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
     ujednoznacz
    -0.58
    неопр
    -0.57
    PickerController
    -0.52
    borderWidth
    -0.52
    irection
    -0.49
     eventdata
    -0.49
    <?
    -0.49
    STARTED
    -0.48
    ưng
    -0.48
     EconPapers
    -0.48
    POSITIVE LOGITS
     final
    0.93
     Dernière
    0.81
     Final
    0.74
    最後
    0.73
     cuối
    0.71
     penultimate
    0.71
    Final
    0.71
     Ostat
    0.68
    GIVEREF
    0.68
     ultimo
    0.68
    Activations Density 0.755%

    No Known Activations