© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5384
    Prev
    Next
    INDEX
    Explanations

    the word "which" and nearby conjunctions or verbs

    oai_token-act-pair · gemini-2.0-flash

    which

    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
     which
    -0.56
     who
    -0.53
    who
    -0.52
    which
    -0.50
    Which
    -0.45
     Which
    -0.44
     Who
    -0.44
     que
    -0.42
    .
    -0.41
     которое
    -0.40
    POSITIVE LOGITS
    Geplaatst
    0.93
    MENAFN
    0.84
    IndentedString
    0.81
    interopRequire
    0.80
    CppMethod
    0.80
    ChildScrollView
    0.77
     Normdatei
    0.76
     оригіналу
    0.76
    Tikang
    0.75
    헌
    0.72
    Activations Density 3.154%

    No Known Activations