© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13395
    Prev
    Next
    INDEX
    Explanations

    descriptive language associated with the horror genre along with descriptions of startling occurences

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "jump"

    np_token-act-pair-logits · gpt-4o-mini

    Jump

    np_max-act-logits · gemini-2.0-flash
    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
     يتيمه
    -0.55
     ExecuteAsync
    -0.54
    caloosa
    -0.45
    chemise
    -0.43
    AccessorTable
    -0.42
     dinámica
    -0.41
     dynamic
    -0.40
    anolamine
    -0.40
     oscu
    -0.40
    less
    -0.40
    POSITIVE LOGITS
     jump
    1.06
     jumps
    0.90
    jump
    0.87
     Jump
    0.85
     Jumps
    0.83
     JUMP
    0.82
    Jump
    0.82
     jumped
    0.82
    JUMP
    0.77
     start
    0.75
    Activations Density 1.673%

    No Known Activations