© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7734
    Prev
    Next
    INDEX
    Explanations

    clauses showing some lack or reduction involving words like "a", "to", "the", "of", "for", and "and"

    oai_token-act-pair · gemini-2.0-flash

    a/an

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    alyptus
    -0.60
    Décès
    -0.58
    KURZBESCHREIBUNG
    -0.58
    Toponymie
    -0.52
    بوابة
    -0.51
    WithIdentifier
    -0.50
    Subview
    -0.49
     being
    -0.48
    losigkeit
    -0.48
    warded
    -0.48
    POSITIVE LOGITS
    --)
    0.53
    /−
    0.52
    [];
    0.49
    MigrationBuilder
    0.49
     noqa
    0.47
     linkovi
    0.46
     sessionFactory
    0.46
     propOrder
    0.46
    abetes
    0.46
    letal
    0.46
    Activations Density 2.670%

    No Known Activations