© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12658
    Prev
    Next
    INDEX
    Explanations

    the word "at" followed by other words

    oai_token-act-pair · gemini-2.0-flash

    at

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    devamını
    -0.74
    __":
    -0.55
    ьаж
    -0.54
    Clik
    -0.53
    listFiles
    -0.52
     estekak
    -0.52
     EClass
    -0.52
    RenderAtEndOf
    -0.52
    migrationBuilder
    -0.51
     EconPapers
    -0.51
    POSITIVE LOGITS
     Jefus
    0.55
     oor
    0.49
    soort
    0.49
     وصلة
    0.48
     laft
    0.46
    prits
    0.45
    Assumptions
    0.45
     الميل
    0.45
     تانيه
    0.45
     preferências
    0.45
    Activations Density 2.164%

    No Known Activations