© 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. 15057
    Prev
    Next
    INDEX
    Explanations

    the word "obviously" and also a smattering of negative judgmental adjectives

    oai_token-act-pair · gemini-2.0-flash

    obviously

    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
     NDEBUG
    -0.81
     whoſe
    -0.79
     $_"
    -0.77
    ]--;
    -0.75
     useAppContext
    -0.74
     unfavourable
    -0.74
     apologise
    -0.73
     diarrhoea
    -0.73
     iſt
    -0.73
     contextLoads
    -0.73
    POSITIVE LOGITS
    <bos>
    0.63
    I
    0.62
     “
    0.60
    等
    0.60
    “
    0.60
    ti
    0.58
    im
    0.56
    A
    0.56
    ف
    0.56
    As
    0.54
    Activations Density 1.514%

    No Known Activations