© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12480
    Prev
    Next
    INDEX
    Explanations

    words related to data analysis and different levels within a technical context.

    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_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    -1.54
     levels
    -1.52
    level
    -1.38
     Level
    -1.36
     Levels
    -1.34
    levels
    -1.34
    Level
    -1.33
     LEVEL
    -1.32
    Levels
    -1.30
     nivel
    -1.27
    POSITIVE LOGITS
    ginfo
    0.62
    Begriffsklä
    0.55
    eqn
    0.52
    exitRule
    0.52
    ciclopedia
    0.52
    bigint
    0.52
     propOrder
    0.51
     nawr
    0.50
    قایناق‌لار
    0.47
    tagHelper
    0.47
    Activations Density 29.421%

    No Known Activations