© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4817
    Prev
    Next
    INDEX
    Explanations

    prepositions, conjunctions, and auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    Населення
    -0.57
     or
    -0.57
     الحره
    -0.54
     GenerationType
    -0.54
    ThemeOverlay
    -0.54
    TemporalType
    -0.54
    المناصب
    -0.53
     или
    -0.53
    aarrggbb
    -0.52
    Или
    -0.52
    POSITIVE LOGITS
    esModule
    0.57
    jsxFileName
    0.56
    contentLoaded
    0.54
    principalTable
    0.52
    GIVEREF
    0.51
    多了
    0.51
     propOrder
    0.50
    unger
    0.49
    nati
    0.49
    QMetaType
    0.49
    Activations Density 21.344%

    No Known Activations