© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2807
    Prev
    Next
    INDEX
    Explanations

    phrases with "make" followed by "a"

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    makes
    -1.09
    MAKE
    -1.07
    make
    -1.06
     makes
    -1.04
    Makes
    -1.02
     Makes
    -1.01
     MAKE
    -1.01
     make
    -1.00
     making
    -0.98
     MAKES
    -0.98
    POSITIVE LOGITS
     com
    0.36
     concor
    0.36
    org
    0.36
     org
    0.35
     al
    0.35
     og
    0.34
     conc
    0.34
     int
    0.33
    L
    0.33
     mi
    0.33
    Activations Density 1.217%

    No Known Activations