© 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. 11923
    Prev
    Next
    INDEX
    Explanations

    words related to placement and positioning

    oai_token-act-pair · gemini-2.0-flash

    position

    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
     position
    -1.37
    position
    -1.28
     Position
    -1.27
     POSITION
    -1.23
     positions
    -1.21
    Position
    -1.20
     positioning
    -1.16
     positioned
    -1.09
    positions
    -1.08
    位置
    -1.08
    POSITIVE LOGITS
     kasarigan
    0.66
    IonicModule
    0.60
     Exacts
    0.58
    AsUp
    0.58
    XmlAccessorType
    0.55
    GraphicsUnit
    0.54
    useNewUrlParser
    0.51
    Становништво
    0.47
    IndentedString
    0.47
    ArrowToggle
    0.45
    Activations Density 22.130%

    No Known Activations