© 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. 3540
    Prev
    Next
    INDEX
    Explanations

    the syllable "bu"

    oai_token-act-pair · gemini-2.0-flash

    bu

    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
    TagMode
    -0.66
    BeginContext
    -0.59
    RenderAtEndOf
    -0.57
    cloudfront
    -0.51
     للاسماء
    -0.51
    NameInMap
    -0.49
    ValueStyle
    -0.49
    RTEX
    -0.49
     referenties
    -0.48
    ]")]
    -0.48
    POSITIVE LOGITS
     NDEBUG
    0.59
     doInBackground
    0.57
     FLOAT
    0.55
    ftrag
    0.54
    dersfield
    0.54
     Prosper
    0.52
     hyperplasia
    0.52
    houettes
    0.51
    endorff
    0.51
    cinogen
    0.50
    Activations Density 0.353%

    No Known Activations