Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10398
    Prev
    Next
    INDEX
    Explanations

    phrases related to deciding between alternatives and knowing which is correct

    oai_token-act-pair · gemini-2.0-flash

    question words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    WAUKEE
    -0.75
     مواليد
    -0.73
    "}")
    -0.70
    ConstraintMaker
    -0.68
    UnsafeEnabled
    -0.66
     CURIAM
    -0.65
     Wikimedijinoj
    -0.65
    setVerticalGroup
    -0.63
    dicionado
    -0.63
    MLLoader
    -0.63
    POSITIVE LOGITS
     Who
    0.98
    Who
    0.96
     who
    0.94
    who
    0.91
     کدام
    0.88
     Which
    0.86
    Which
    0.82
     hangi
    0.81
     quién
    0.81
    誰
    0.81
    Activations Density 0.867%

    No Known Activations