© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5052
    Prev
    Next
    INDEX
    Explanations

    the words "nearby", "true", or "truth", along with some adjectives (higher, typical, entire)

    oai_token-act-pair · gemini-2.0-flash

    location and truth

    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
    :✨
    -0.82
    WithIOException
    -0.77
    #+#
    -0.71
    CodeAttribute
    -0.69
    LookAnd
    -0.67
    IntoConstraints
    -0.67
    
    -0.66
    حياتها
    -0.65
    jsxFileName
    -0.63
    
    -0.62
    POSITIVE LOGITS
    <bos>
    0.63
    ödie
    0.54
     Seeing
    0.52
    bewerken
    0.51
     seeing
    0.49
    ↵↵
    0.49
    Seeing
    0.48
     way
    0.48
     broader
    0.47
     utilizing
    0.46
    Activations Density 0.397%

    No Known Activations