© 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. 9773
    Prev
    Next
    INDEX
    Explanations

    words related to measurements, comparisons and scientific studies

    oai_token-act-pair · gemini-2.0-flash

    multi-language tokens

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

    technical/scientific texts

    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
     similar
    -1.39
    similar
    -1.23
    Similar
    -1.21
     Similar
    -1.16
     ähnlichen
    -1.02
     semelhante
    -0.98
     SIMILAR
    -0.96
     similaire
    -0.95
     similaires
    -0.94
     similares
    -0.93
    POSITIVE LOGITS
     as
    0.52
    ftagPool
    0.47
     аса
    0.47
     насељу
    0.46
     Birken
    0.45
    بور
    0.44
    iono
    0.44
    hydrogenase
    0.44
    senha
    0.43
    wię
    0.43
    Activations Density 12.462%

    No Known Activations