© 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. 14510
    Prev
    Next
    INDEX
    Explanations

    mentions of groups of people, proper nouns, or superlatives relating to population and time

    oai_token-act-pair · gemini-2.0-flash

    technical terms or identifiers

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

    say apostrophe

    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
    ,
    -0.69
     
    -0.68
     the
    -0.65
     I
    -0.63
     a
    -0.60
     Z
    -0.59
     in
    -0.59
     and
    -0.58
     (
    -0.58
     i
    -0.57
    POSITIVE LOGITS
    GEBURTSDATUM
    0.94
     NSCoder
    0.84
    OGND
    0.83
    ՚
    0.82
    
    0.81
     AssemblyVersion
    0.76
     CascadeType
    0.76
     auffi
    0.75
     apos
    0.75
    ′
    0.73
    Activations Density 1.312%

    No Known Activations