© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13747
    Prev
    Next
    INDEX
    Explanations

    words related to the chemistry of silanes and polymers

    oai_token-act-pair · gemini-2.0-flash

    chemical compounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Datuak
    -0.60
     AssemblyTitle
    -0.58
    <bos>
    -0.54
     pym
    -0.49
    ulele
    -0.48
    ...');
    -0.47
    ymce
    -0.45
    ciss
    -0.44
     виправивши
    -0.44
    ország
    -0.44
    POSITIVE LOGITS
    ]")]
    0.75
     métiers
    0.63
    ollection
    0.62
     TextInputType
    0.59
    رشف
    0.57
     Exacts
    0.56
     sélection
    0.52
     صفر
    0.52
     papiers
    0.52
     vermelhas
    0.52
    Activations Density 52.467%

    No Known Activations