© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2501
    Prev
    Next
    INDEX
    Explanations

    the word "type" followed by "of"

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating type or category

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

    type, kind, sort

    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
     kind
    -2.16
     type
    -1.95
    kind
    -1.86
    Kind
    -1.82
     kinds
    -1.80
     Kind
    -1.72
    type
    -1.70
     types
    -1.69
     sort
    -1.59
     tipo
    -1.57
    POSITIVE LOGITS
    펙
    0.46
    ostat
    0.46
    camento
    0.44
    #![
    0.42
    GroupName
    0.42
    maksi
    0.41
     Weiner
    0.41
    bjs
    0.41
    ReadLine
    0.41
     fruit
    0.40
    Activations Density 1.138%

    No Known Activations