© 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. 7608
    Prev
    Next
    INDEX
    Explanations

    personal opinions, financial terms, and pronouns

    oai_token-act-pair · gemini-2.0-flash

    the word "make"

    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
     /\.
    -0.59
    parsedMessage
    -0.55
    binaan
    -0.51
     án
    -0.51
     Kiy
    -0.49
    DTD
    -0.49
    ̀n
    -0.47
    inhua
    -0.46
     Alg
    -0.45
    âng
    -0.45
    POSITIVE LOGITS
     making
    2.16
     make
    2.08
     Making
    2.02
    Making
    1.98
     makes
    1.98
    Make
    1.95
    make
    1.94
     Make
    1.89
    making
    1.88
    makes
    1.84
    Activations Density 2.736%

    No Known Activations