© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6471
    Prev
    Next
    INDEX
    Explanations

    the phrase "hard to"

    oai_token-act-pair · gemini-2.0-flash

    hard

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     difficiles
    -0.50
     difíciles
    -0.45
    hard
    -0.45
    FromArgb
    -0.43
    hards
    -0.43
     compleja
    -0.42
     hard
    -0.39
    COMPLEX
    -0.39
    хла
    -0.39
    HARD
    -0.39
    POSITIVE LOGITS
    CloseOperation
    0.82
     Monfieur
    0.81
    CreateModel
    0.77
    sizeCache
    0.75
     ویکی‌پدیای
    0.74
    migrationBuilder
    0.72
    bootstrapcdn
    0.71
    RegressionTest
    0.71
    windowFixed
    0.71
    WireFormatLite
    0.69
    Activations Density 0.497%

    No Known Activations