© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1506
    Prev
    Next
    INDEX
    Explanations

    prepositions and helping verbs

    oai_token-act-pair · gemini-2.0-flash

    state of being "on" something

    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
     <<<<<<<<<<<<<<
    -0.89
    Демографія
    -0.79
    tagext
    -0.79
    AndEndTag
    -0.75
    WriteTagHelper
    -0.75
    StoryboardSegue
    -0.74
    ništ
    -0.74
     Мексичка
    -0.73
     незавершена
    -0.73
    BeginContext
    -0.71
    POSITIVE LOGITS
     on
    1.96
    On
    1.40
     On
    1.36
    on
    1.15
     ON
    1.03
     على
    0.87
    オン
    0.86
     на
    0.85
     board
    0.82
    onthe
    0.74
    Activations Density 2.812%

    No Known Activations