© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8376
    Prev
    Next
    INDEX
    Explanations

    sentences that describe a sequence of events involving someone picking up someone else and going somewhere

    oai_token-act-pair · gemini-2.0-flash

    pick

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    +:+
    -0.84
     AssemblyCulture
    -0.82
     समीक्षाओं
    -0.81
    MemoryWarning
    -0.80
    GraphicsUnit
    -0.71
    InstanceState
    -0.71
     الحره
    -0.71
    ьаж
    -0.70
    tvguidetime
    -0.69
    :+:
    -0.68
    POSITIVE LOGITS
     pick
    1.78
     Pick
    1.63
     pickup
    1.59
    pick
    1.59
    Pick
    1.57
     picked
    1.48
     PICK
    1.48
     Pickup
    1.38
    PICK
    1.37
     picking
    1.36
    Activations Density 0.510%

    No Known Activations