© 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. 9248
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly focusing on attributes, restaurant data, and tags

    oai_token-act-pair · gemini-2.0-flash

    unique or non-standard terms

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

    say 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
     =
    -0.73
    ⓧ
    -0.60
    =
    -0.59
     h
    -0.56
     mo
    -0.54
    HttpFoundation
    -0.54
    soni
    -0.54
     Bo
    -0.54
    اة
    -0.54
     o
    -0.52
    POSITIVE LOGITS
    ſelves
    0.72
    NUMX
    0.68
     للاسماء
    0.66
    Izvori
    0.65
     Normdatei
    0.65
    Amicalement
    0.63
    felves
    0.63
     itſelf
    0.62
    AndEndTag
    0.62
     actionPerformed
    0.62
    Activations Density 7.366%

    No Known Activations