© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15127
    Prev
    Next
    INDEX
    Explanations

    the preposition "on"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    fromnode
    -0.66
    ništ
    -0.56
    DrawerToggle
    -0.54
    Tembelea
    -0.53
    ensuremath
    -0.53
    FFIX
    -0.51
    εί
    -0.50
     ControllerBase
    -0.50
    routeProvider
    -0.50
    onOptions
    -0.50
    POSITIVE LOGITS
    DebuggerNonUser
    0.56
    findpost
    0.51
    Gön
    0.50
     trenches
    0.49
    şı
    0.47
    rawDesc
    0.45
     stá
    0.45
    Vidite
    0.45
    EditorBrowsable
    0.45
    Personensuche
    0.45
    Activations Density 2.674%

    No Known Activations