© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13034
    Prev
    Next
    INDEX
    Explanations

    snippets of French text including verbs and other common grammatical elements.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     HttpNotFound
    -0.81
    anmoins
    -0.78
     Monfieur
    -0.72
     Efq
    -0.70
     kaynağından
    -0.69
    UnusedPrivate
    -0.68
     Jefus
    -0.68
     poffible
    -0.66
     himſelf
    -0.66
    saturated
    -0.65
    POSITIVE LOGITS
    <bos>
    0.66
    BeginContext
    0.61
    >(&
    0.54
     of
    0.49
    magini
    0.49
     Indien
    0.47
    ')")
    0.46
    |<\
    0.45
     zasad
    0.43
    nextDouble
    0.43
    Activations Density 1.489%

    No Known Activations