© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12904
    Prev
    Next
    INDEX
    Explanations

    words discussing movement and travel both physical and molecular

    oai_token-act-pair · gemini-2.0-flash

    movement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    PerformLayout
    -0.80
     propOrder
    -0.78
    UrlResolution
    -0.74
     cherchés
    -0.73
    Enllaços
    -0.73
    AutoScaleMode
    -0.71
     ExecuteAsync
    -0.70
    ImageContext
    -0.70
     كومونز
    -0.68
    Бахар
    -0.67
    POSITIVE LOGITS
     movement
    1.39
    movement
    1.16
     Movement
    1.14
    Movement
    1.09
     MOVEMENT
    1.00
     movements
    0.97
     mouvement
    0.91
     movimento
    0.90
     motion
    0.89
     movimiento
    0.88
    Activations Density 1.761%

    No Known Activations