© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9988
    Prev
    Next
    INDEX
    Explanations

    instances of the word "I" or "you", potentially with the context of doing or wanting to do something

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     getting
    -0.79
     Getting
    -0.75
    getting
    -0.72
    Getting
    -0.70
     Gets
    -0.63
     gets
    -0.63
     GETTING
    -0.61
    Gets
    -0.59
    COUVER
    -0.58
    GETTING
    -0.57
    POSITIVE LOGITS
    ⓧ
    0.69
     Conſ
    0.64
    LookAnd
    0.62
     taught
    0.60
     pleaſure
    0.59
     ruled
    0.59
     inserted
    0.58
     Diſ
    0.57
     εφ
    0.57
     write
    0.57
    Activations Density 8.372%

    No Known Activations