© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11844
    Prev
    Next
    INDEX
    Explanations

    the word "bond" in legal or scientific contexts

    oai_token-act-pair · gemini-2.0-flash

    bond

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -0.89
    verwijspagina
    -0.86
    itisation
    -0.75
    +#+#
    -0.69
    abestanden
    -0.67
    DataBean
    -0.67
    initialise
    -0.63
    bogen
    -0.63
    inei
    -0.63
     Club
    -0.62
    POSITIVE LOGITS
    gameserver
    0.69
     pantaloni
    0.58
     elefante
    0.57
     argint
    0.56
    มาะ
    0.55
     alberi
    0.55
     célèbres
    0.55
     pouvoit
    0.55
     gratuits
    0.54
     feroit
    0.54
    Activations Density 1.187%

    No Known Activations