© 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. 12456
    Prev
    Next
    INDEX
    Explanations

    the word "collective" and other words with shared meaning, but also finds some words such as "rose" and "that"

    oai_token-act-pair · gemini-2.0-flash

    collective

    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
     formales
    -0.89
     spørsmål
    -0.83
     femininas
    -0.83
     culturelles
    -0.83
     enfans
    -0.82
     connus
    -0.82
     illustrazione
    -0.82
     lèvres
    -0.81
     partag
    -0.80
     connues
    -0.80
    POSITIVE LOGITS
    tages
    0.62
     benefic
    0.59
    ttes
    0.59
     Alco
    0.59
     imper
    0.57
     Dire
    0.57
    getCurrent
    0.56
    tagens
    0.54
    itag
    0.52
    valdo
    0.52
    Activations Density 2.599%

    No Known Activations