© 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. 14599
    Prev
    Next
    INDEX
    Explanations

    text mentioning dates and times

    oai_token-act-pair · gemini-2.0-flash

    punctuation and common conjunctions

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

    time periods

    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
     itſelf
    -0.95
     disambiguazione
    -0.88
    씩
    -0.85
     snippetHide
    -0.83
    شهاد
    -0.81
    $_['
    -0.80
     насељу
    -0.80
    ValueStyle
    -0.80
    ={({
    -0.79
     caufe
    -0.76
    POSITIVE LOGITS
    .
    0.56
     for
    0.51
     müm
    0.47
    jemahan
    0.45
     cervello
    0.45
    ,
    0.44
     petto
    0.42
     tarvit
    0.41
     mahdol
    0.41
     pushing
    0.41
    Activations Density 8.804%

    No Known Activations