© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 9869
    Prev
    Next
    INDEX
    Explanations

    the word "underlying" and words that sometimes precede it

    oai_token-act-pair · gemini-2.0-flash

    underlying

    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
     few
    -0.93
     more
    -0.92
     other
    -0.88
     new
    -0.87
     newly
    -0.87
     three
    -0.85
     recently
    -0.85
     two
    -0.85
     others
    -0.85
     former
    -0.84
    POSITIVE LOGITS
    <bos>
    1.26
    
    1.16
     CreateTagHelper
    1.02
     ProtoMessage
    0.99
     Мексичка
    0.91
    posedge
    0.91
    tagHelperRunner
    0.91
     resourceCulture
    0.88
    ]")]
    0.84
    SPATH
    0.83
    Activations Density 0.947%

    No Known Activations