© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15073
    Prev
    Next
    INDEX
    Explanations

    uses of the words 'on', 'by', or 'the' in various contexts

    oai_token-act-pair · gemini-2.0-flash

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     виправивши
    -0.73
    GEBURTSDATUM
    -0.58
    ysacchar
    -0.54
    ApiOperation
    -0.51
     estekak
    -0.49
    Portail
    -0.48
    BeginContext
    -0.46
    ↘
    -0.46
     مشين
    -0.46
    vician
    -0.45
    POSITIVE LOGITS
    GHIJKLM
    0.59
    apimachinery
    0.57
    клопе
    0.56
    AnchorTagHelper
    0.56
    térature
    0.55
    complexContent
    0.55
     оригіналу
    0.54
    CopyWith
    0.54
     كمان
    0.50
    őtt
    0.50
    Activations Density 0.544%

    No Known Activations