© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5019
    Prev
    Next
    INDEX
    Explanations

    the word "has" or "have" within a sentence, especially when followed by certain adverbs or past participles

    oai_token-act-pair · gemini-2.0-flash

    been

    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
     be
    -1.31
    Be
    -1.25
     Be
    -1.21
    be
    -1.11
     BE
    -0.90
     soient
    -0.86
    BE
    -0.77
     was
    -0.68
     sejam
    -0.62
     puissent
    -0.61
    POSITIVE LOGITS
     been
    1.37
    GraphicsUnit
    0.74
    OGND
    0.73
    been
    0.70
    WebServlet
    0.69
     BEEN
    0.69
    Been
    0.68
     Been
    0.65
     gewesen
    0.62
     tslint
    0.62
    Activations Density 1.365%

    No Known Activations