© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1232
    Prev
    Next
    INDEX
    Explanations

    the word "level", numbers or measurements and financial terms

    oai_token-act-pair · gemini-2.0-flash

    level

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     level
    -2.75
    level
    -2.45
     Level
    -2.44
    Level
    -2.44
     LEVEL
    -2.33
     levels
    -2.25
    LEVEL
    -2.08
    levels
    -2.03
     Levels
    -2.02
    Levels
    -1.88
    POSITIVE LOGITS
     Trag
    0.52
    ضم
    0.50
     Zug
    0.50
    StateException
    0.48
     applicazioni
    0.47
     descans
    0.45
     Pits
    0.45
     geweest
    0.44
     obyvateľov
    0.44
    assertThrows
    0.44
    Activations Density 1.868%

    No Known Activations