© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7336
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to asking questions, especially in a formal setting.

    oai_token-act-pair · gemini-2.0-flash

    questions and asking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     questions
    -2.84
     question
    -2.84
     Question
    -2.72
     Questions
    -2.58
    Question
    -2.56
    question
    -2.53
    questions
    -2.52
    Questions
    -2.47
     QUESTION
    -2.39
     Frage
    -2.23
    POSITIVE LOGITS
    tanleria
    0.59
     فريبيس
    0.56
     rhestr
    0.46
     ddelweddau
    0.46
     Référence
    0.43
    writeValue
    0.43
    FXMLLoader
    0.42
    ésia
    0.42
     fleste
    0.42
    นะนำ
    0.41
    Activations Density 2.410%

    No Known Activations