© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13542
    Prev
    Next
    INDEX
    Explanations

    words related to the environment, atmosphere, and basic elements

    oai_token-act-pair · gemini-2.0-flash

    atmosphere

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     NSCoder
    -0.65
     GetEnumerator
    -0.63
     enfans
    -0.60
    collant
    -0.60
     Investigaciones
    -0.58
    collants
    -0.58
     whoſe
    -0.57
     ویکی‌پدیا
    -0.55
    assertAll
    -0.55
     pagare
    -0.55
    POSITIVE LOGITS
     space
    0.69
     SPACE
    0.68
    istocene
    0.62
     Space
    0.60
     Luf
    0.60
     breathed
    0.59
     utafitiHapana
    0.59
    Luft
    0.59
     airspace
    0.57
    itespace
    0.56
    Activations Density 3.233%

    No Known Activations