© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3865
    Prev
    Next
    INDEX
    Explanations

    the word "bu" or related words, plus maybe chemistry or medicine terms.

    oai_token-act-pair · gemini-2.0-flash

    bu

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Bu
    -1.65
     bu
    -1.62
    Bu
    -1.45
    bu
    -1.34
    BU
    -1.19
     BU
    -1.11
     Bul
    -0.95
     Bur
    -0.94
     BUL
    -0.93
    бу
    -0.92
    POSITIVE LOGITS
     يتيمه
    0.59
     öne
    0.45
     PARSER
    0.44
     väli
    0.42
     đáo
    0.41
     MPR
    0.41
    ctp
    0.41
    mmings
    0.40
    ähle
    0.40
    šlo
    0.40
    Activations Density 8.480%

    No Known Activations