© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6211
    Prev
    Next
    INDEX
    Explanations

    words related to walking

    oai_token-act-pair · gemini-2.0-flash

    Research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     movement
    -1.12
     Movement
    -1.11
    Movement
    -1.09
     MOVEMENT
    -1.00
     motion
    -1.00
     Bewegung
    -0.99
    movement
    -0.98
     movimiento
    -0.97
     Motion
    -0.94
    Motion
    -0.94
    POSITIVE LOGITS
    TagMode
    0.82
     Paglinawan
    0.70
     سكانية
    0.69
    InstrumentedTest
    0.68
     Signalez
    0.66
    Geplaatst
    0.64
    Solución
    0.63
    ViewImports
    0.60
     endwhile
    0.60
    principalColumn
    0.59
    Activations Density 2.230%

    No Known Activations