© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6639
    Prev
    Next
    INDEX
    Explanations

    words related to school and dancing.

    oai_token-act-pair · gemini-2.0-flash

    dance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    !*\
    -0.46
    styleType
    -0.45
    orsese
    -0.44
     دیکھیے
    -0.44
    SuspendLayout
    -0.42
     okuyayım
    -0.41
    ddots
    -0.40
    μισ
    -0.40
     AppColors
    -0.39
     menem
    -0.39
    POSITIVE LOGITS
     Audiodateien
    0.86
    +#+#
    0.78
     المعيارى
    0.67
    MigrationBuilder
    0.66
    antMatchers
    0.65
    EReference
    0.63
    findpost
    0.61
    setVerticalGroup
    0.61
    BackStack
    0.59
    ]--;
    0.58
    Activations Density 1.464%

    No Known Activations