© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10379
    Prev
    Next
    INDEX
    Explanations

    parts of words that are prefixes, suffixes, or word stems

    oai_token-act-pair · gemini-2.0-flash

    technical programming or coding terms

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

    respir

    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
    #
    -0.62
     ExecuteAsync
    -0.62
     mink
    -0.57
    uza
    -0.53
    CodeAttribute
    -0.52
     proviso
    -0.52
    SaveChangesAsync
    -0.52
    PerformLayout
    -0.51
     SOLID
    -0.51
     <<<<<<<<<<<<<<
    -0.50
    POSITIVE LOGITS
    tanleria
    0.61
    istoitu
    0.51
     discorso
    0.49
     beginnetje
    0.48
    mybatisplus
    0.47
    tvguidetime
    0.47
    Imper
    0.46
     S
    0.46
    DeleteBehavior
    0.45
     jsPsych
    0.45
    Activations Density 2.255%

    No Known Activations