© 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. 13026
    Prev
    Next
    INDEX
    Explanations

    instances of the word "substance" and its plural form along with related words like impurities or imperfections

    oai_token-act-pair · gemini-2.0-flash

    substance

    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
    ↵↵
    -1.20
     
    -0.77
    2
    -0.77
    ↵
    -0.76
    4
    -0.72
    1
    -0.72
    <strong>
    -0.71
    The
    -0.69
    '
    -0.69
    "
    -0.67
    POSITIVE LOGITS
    ícone
    1.05
    guiente
    1.04
     lenker
    1.01
     RIPRODUZIONE
    0.97
    Lähteet
    0.96
    RTEE
    0.96
    новништво
    0.94
    boneca
    0.94
    drawal
    0.94
    Atentamente
    0.93
    Activations Density 0.901%

    No Known Activations