© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15112
    Prev
    Next
    INDEX
    Explanations

    words related to scientific research and data analysis

    oai_token-act-pair · gemini-2.0-flash

    verbs related to movement or transfer

    np_token-act-pair-logits · gpt-4o-mini

    movement/transfer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     manqué
    -0.52
    /**
    -0.49
     urbanas
    -0.49
     contratar
    -0.45
     bolsillo
    -0.45
     supérieurs
    -0.45
     détruit
    -0.44
     caseros
    -0.44
    近
    -0.43
     africains
    -0.42
    POSITIVE LOGITS
     movement
    1.48
     transfer
    1.43
     moving
    1.36
     move
    1.36
     moved
    1.34
    move
    1.31
     Movement
    1.31
     transfers
    1.30
     transferring
    1.30
    movement
    1.27
    Activations Density 4.361%

    No Known Activations