© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11577
    Prev
    Next
    INDEX
    Explanations

    the word "guess."

    oai_token-act-pair · gemini-2.0-flash

    guess

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    migrationBuilder
    -0.83
     guess
    -0.79
     nî
    -0.68
    CppCodeGen
    -0.64
    reel
    -0.64
     supposition
    -0.63
     ConstraintSet
    -0.63
     SPRINGS
    -0.63
     trial
    -0.62
     Guess
    -0.62
    POSITIVE LOGITS
    <bos>
    0.73
     }}</
    0.50
    }}</
    0.50
    )}</
    0.49
     na
    0.44
     Sol
    0.44
    ˈ
    0.43
    kező
    0.43
     invokingState
    0.43
     [[
    0.43
    Activations Density 1.315%

    No Known Activations