© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14384
    Prev
    Next
    INDEX
    Explanations

    the word "after" as well as related words like "time", "the", and "era".

    oai_token-act-pair · gemini-2.0-flash

    structured data points or sequences

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    ப்பட்டது
    -0.52
     artikke
    -0.50
     invokingState
    -0.48
    basedir
    -0.48
     it
    -0.46
    path
    -0.45
     apellidos
    -0.44
     baw
    -0.44
    migrationBuilder
    -0.43
    uot
    -0.43
    POSITIVE LOGITS
    BeginContext
    0.71
     crossorigin
    0.68
    tagHelperRunner
    0.60
    lorette
    0.53
    ograma
    0.52
    <!--[
    0.52
    الحياه
    0.51
    endswith
    0.51
     lacto
    0.50
    Geplaatst
    0.49
    Activations Density 0.517%

    No Known Activations