© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11866
    Prev
    Next
    INDEX
    Explanations

    words used when making a claim about an invention

    oai_token-act-pair · gemini-2.0-flash

    become

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     like
    -1.61
    like
    -1.33
     LIKE
    -1.29
    Like
    -1.27
     Like
    -1.27
    LIKE
    -1.12
     مانند
    -0.88
     seperti
    -0.85
     כמו
    -0.84
    seperti
    -0.83
    POSITIVE LOGITS
     became
    0.96
     becomes
    0.96
     become
    0.92
    became
    0.76
     becoming
    0.76
    becomes
    0.75
    become
    0.71
     Become
    0.69
     Becomes
    0.67
    Becoming
    0.65
    Activations Density 1.605%

    No Known Activations