© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13038
    Prev
    Next
    INDEX
    Explanations

    the word "specific" and words that commonly go with it.

    oai_token-act-pair · gemini-2.0-flash

    vocabulary related to specificity and categorization

    np_token-act-pair-logits · gpt-4o-mini

    specific

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     particular
    -1.13
    particular
    -1.09
    certain
    -1.02
     certain
    -1.01
     tertentu
    -0.97
     Particular
    -0.97
    Certain
    -0.95
     Certain
    -0.94
     PARTICULAR
    -0.90
     CERTAIN
    -0.88
    POSITIVE LOGITS
     type
    0.69
     types
    0.61
     aspect
    0.54
    IsContent
    0.52
     propOrder
    0.48
     Type
    0.47
    type
    0.47
     category
    0.47
     format
    0.46
     combination
    0.46
    Activations Density 2.604%

    No Known Activations