© 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. 3749
    Prev
    Next
    INDEX
    Explanations

    words related to technology, entertainment, and product reviews

    oai_token-act-pair · gemini-2.0-flash

    back

    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
    posedge
    -0.51
    ļas
    -0.46
    wijl
    -0.44
    nja
    -0.43
     незавершена
    -0.41
    RunWith
    -0.40
     externi
    -0.40
     pageable
    -0.40
     Extragalactic
    -0.39
    ברים
    -0.39
    POSITIVE LOGITS
     back
    3.89
     Back
    3.03
    back
    3.02
    Back
    3.00
     BACK
    2.80
    BACK
    2.61
    backs
    2.06
     backs
    1.98
    バック
    1.85
     tilbake
    1.80
    Activations Density 4.898%

    No Known Activations