© 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. 7847
    Prev
    Next
    INDEX
    Explanations

    words related to gardening or other outdoor hobbies

    oai_token-act-pair · gemini-2.0-flash

    informal or casual language

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

    blog posts

    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
    >);
    -0.68
    oredCriteria
    -0.66
     communs
    -0.65
    CppMethod
    -0.63
    *;
    -0.62
     linkovi
    -0.60
    ’;
    -0.59
     damska
    -0.58
    '>";
    -0.57
     mourir
    -0.57
    POSITIVE LOGITS
    cdnjs
    0.50
     But
    0.50
    횟
    0.49
    ParallelGroup
    0.48
     насељу
    0.46
    梗
    0.45
    wot
    0.45
     !
    0.45
     but
    0.44
    upyter
    0.44
    Activations Density 8.342%

    No Known Activations