© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12770
    Prev
    Next
    INDEX
    Explanations

    the word "question" and related words

    oai_token-act-pair · gemini-2.0-flash

    question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     question
    -2.91
    question
    -2.33
     Question
    -2.22
    Question
    -2.09
     QUESTION
    -1.86
     questions
    -1.83
     Frage
    -1.82
    QUESTION
    -1.65
     Questions
    -1.55
    questions
    -1.53
    POSITIVE LOGITS
    AndEndTag
    0.79
    principalTable
    0.77
    AccessorTable
    0.74
     '\\;'
    0.64
     SafeMath
    0.63
    脚注の使い方
    0.62
     AssemblyCulture
    0.62
    Hochspringen
    0.61
    PerformLayout
    0.60
    DIPSETTING
    0.59
    Activations Density 1.093%

    No Known Activations