© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6400
    Prev
    Next
    INDEX
    Explanations

    uses of conjunctions like 'and' and 'but' followed by personal pronouns or expressions of opinion

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ########.
    -1.00
     CreateTagHelper
    -0.90
     utafitiHapana
    -0.83
     estekak
    -0.76
     виправивши
    -0.75
    homonymie
    -0.74
     snippetHide
    -0.71
     AssemblyProduct
    -0.70
    onViewCreated
    -0.70
    verwijspagina
    -0.69
    POSITIVE LOGITS
     thought
    0.50
     need
    0.50
     have
    0.49
     think
    0.49
     appréci
    0.47
     recognize
    0.45
     fréquent
    0.44
     believe
    0.43
     when
    0.43
     prefer
    0.43
    Activations Density 1.591%

    No Known Activations