© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9783
    Prev
    Next
    INDEX
    Explanations

    words related to planning, preparing, and bringing supplies

    oai_token-act-pair · gemini-2.0-flash

    Packing for a trip

    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
    +#+#
    -0.68
     estekak
    -0.68
    writeFieldEnd
    -0.65
     незавершена
    -0.61
    ########.
    -0.60
     CreateTagHelper
    -0.58
    Hozzáférés
    -0.58
    rsiniz
    -0.56
    Espèce
    -0.54
    ͕
    -0.54
    POSITIVE LOGITS
     bug
    0.49
     change
    0.49
     paper
    0.49
    nodoc
    0.48
    dauer
    0.46
    čnost
    0.46
     jump
    0.45
    glEnd
    0.44
     mud
    0.43
     mừng
    0.42
    Activations Density 1.222%

    No Known Activations