© 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. 12063
    Prev
    Next
    INDEX
    Explanations

    phrases expressing opinions or ways of doing things

    oai_token-act-pair · gemini-2.0-flash

    Ways/Way

    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
    SourceChecksum
    -1.00
    expandindo
    -0.85
     समीक्षाओं
    -0.83
     EconPapers
    -0.82
    })*/
    -0.75
     propOrder
    -0.74
    ]<<"
    -0.73
     Autorizaciones
    -0.70
     Roskov
    -0.68
    DrawerToggle
    -0.67
    POSITIVE LOGITS
    +
    0.41
    •
    0.39
     (
    0.38
    其妙
    0.38
    ~
    0.36
    offsetTop
    0.36
     &
    0.36
    taobao
    0.35
    críbete
    0.35
     both
    0.35
    Activations Density 1.454%

    No Known Activations