© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12727
    Prev
    Next
    INDEX
    Explanations

    words related to chemistry, particularly elements and compounds.

    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_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ETRY
    -0.51
    homonymie
    -0.50
    Sidenav
    -0.46
    moor
    -0.46
    RICULUM
    -0.45
     chambers
    -0.45
    andri
    -0.44
    RatingBar
    -0.43
    <bos>
    -0.42
     carbon
    -0.42
    POSITIVE LOGITS
     textStatus
    0.72
     Anſ
    0.71
     Jefus
    0.69
     étoit
    0.66
     quæ
    0.63
     purpoſe
    0.63
     anſ
    0.62
     themſelves
    0.62
     Chriftian
    0.62
     vettoriale
    0.61
    Activations Density 3.457%

    No Known Activations