© 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. 12665
    Prev
    Next
    INDEX
    Explanations

    the word "data" and the word "information"

    oai_token-act-pair · gemini-2.0-flash

    data

    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
     الحره
    -0.67
    apimachinery
    -0.66
     виправивши
    -0.60
    SpringRunner
    -0.56
    orianCalendar
    -0.56
    medriver
    -0.56
    Obrázky
    -0.55
    __":
    -0.55
    brada
    -0.54
    ngrx
    -0.54
    POSITIVE LOGITS
    encodeWith
    0.54
    InputTagHelper
    0.53
    glGen
    0.50
     Приступљено
    0.49
     surla
    0.49
     recul
    0.48
     копия
    0.45
     piede
    0.44
    weck
    0.44
     Malk
    0.44
    Activations Density 0.246%

    No Known Activations