© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12089
    Prev
    Next
    INDEX
    Explanations

    the word "thing" or a plural version of the word

    oai_token-act-pair · gemini-2.0-flash

    thing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -0.68
    ↵↵
    -0.65
    bekah
    -0.52
    Rather
    -0.47
    ioen
    -0.47
    Calculating
    -0.47
    Pretty
    -0.46
     Alamy
    -0.46
    Collegamenti
    -0.45
     Cheaper
    -0.45
    POSITIVE LOGITS
     Ее
    0.73
     Zijn
    0.72
     gyhoeddwyd
    0.71
    Rhestr
    0.68
    GraphicsUnit
    0.68
     jspb
    0.67
     varandra
    0.67
     hendes
    0.66
    出版年
    0.66
    những
    0.66
    Activations Density 0.126%

    No Known Activations