© 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. 2507
    Prev
    Next
    INDEX
    Explanations

    the word "able" or words related to computer programming or legal terminology.

    oai_token-act-pair · gemini-2.0-flash

    2

    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
    ValueStyle
    -1.84
    SourceChecksum
    -1.82
     متعلقه
    -1.81
     CreateTagHelper
    -1.67
     autorytatywna
    -1.65
    webElementXpaths
    -1.64
    tagHelperRunner
    -1.63
     nahilalakip
    -1.63
     AssemblyCulture
    -1.62
    RegressionTest
    -1.62
    POSITIVE LOGITS
     varandra
    -0.02
     étoit
    -0.06
     gratuitas
    -0.09
     temporales
    -0.10
     auroit
    -0.11
     pouvoit
    -0.11
     sebou
    -0.12
     igång
    -0.13
     regeringen
    -0.13
     feroit
    -0.13
    Activations Density 4.567%

    No Known Activations