© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11250
    Prev
    Next
    INDEX
    Explanations

    instances of the word "come" and its variations, sometimes in the context of moving away from something

    oai_token-act-pair · gemini-2.0-flash

    coming/away from

    np_max-act-logits · 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
     from
    -2.42
    จาก
    -1.53
    from
    -1.46
     dari
    -1.42
     från
    -1.27
     từ
    -1.26
     از
    -1.24
     desde
    -1.22
    从
    -1.21
    從
    -1.11
    POSITIVE LOGITS
    expandindo
    0.70
     &___
    0.69
     nahilalakip
    0.66
    Спасылкі
    0.65
    FORM
    0.63
     Form
    0.63
    ContentAsync
    0.61
    WriteTagHelper
    0.59
    forme
    0.57
     MessageBoxIcon
    0.57
    Activations Density 0.684%

    No Known Activations