© 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. 4644
    Prev
    Next
    INDEX
    Explanations

    language related to career planning for the current generation

    oai_token-act-pair · gemini-2.0-flash

    careers and jobs

    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
    LookAnd
    -1.00
     HasFactory
    -0.83
    AddTagHelper
    -0.79
    niająca
    -0.79
     ✭✭
    -0.75
     lenker
    -0.75
    tvguidetime
    -0.74
     SearchView
    -0.73
     resourceCulture
    -0.73
    webElementXpaths
    -0.71
    POSITIVE LOGITS
     official
    0.40
    shar
    0.40
     ار
    0.40
     Farr
    0.40
     job
    0.40
    pfe
    0.39
     medio
    0.39
     __
    0.39
    ][
    0.39
     drive
    0.39
    Activations Density 5.663%

    No Known Activations