© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2046
    Prev
    Next
    INDEX
    Explanations

    the french preposition "de" or the portuguese preposition "de".

    oai_token-act-pair · gemini-2.0-flash

    expressions involving the word 'de'

    np_token-act-pair-logits · gpt-4o-mini

    Tech-related texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Paglinawan
    -0.89
    DatabaseError
    -0.82
     bénéfices
    -0.80
     pleaſure
    -0.76
    ArgsConstructor
    -0.75
     enfans
    -0.73
     greateſt
    -0.71
     morire
    -0.71
    CompilerServices
    -0.70
     Monfieur
    -0.69
    POSITIVE LOGITS
     cat
    0.44
    niejsza
    0.43
     regular
    0.42
     dis
    0.42
     ($_
    0.40
    WritableDatabase
    0.39
    ($_
    0.38
     normal
    0.38
     sh
    0.38
     routine
    0.38
    Activations Density 0.436%

    No Known Activations