© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 45
    Prev
    Next
    INDEX
    Explanations

    language related to scientific study or legal testimony, as well as general scientific terminology

    oai_token-act-pair · gemini-2.0-flash

    consistency and equality

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     equally
    -0.68
     noires
    -0.62
     actores
    -0.53
     Equally
    -0.52
    optarg
    -0.52
     faudra
    -0.51
    Facades
    -0.51
     fabia
    -0.50
     alternatively
    -0.49
     igualmente
    -0.49
    POSITIVE LOGITS
     consistent
    1.96
    consistent
    1.73
     Consistent
    1.68
    Consistent
    1.63
     equal
    1.50
     inconsistent
    1.26
    equal
    1.19
     consistente
    1.07
     Equal
    1.07
     EQUAL
    1.02
    Activations Density 20.327%

    No Known Activations