© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15368
    Prev
    Next
    INDEX
    Explanations

    code imports and Android content references

    oai_token-act-pair · gemini-2.0-flash

    specific content formats or identifiers

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

    code package information

    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
    Negative Logits
     i
    -0.44
     n
    -0.44
     die
    -0.40
    ico
    -0.39
     primary
    -0.39
    .
    -0.39
     e
    -0.39
    nungen
    -0.38
     I
    -0.38
     by
    -0.38
    POSITIVE LOGITS
     فريبيس
    1.09
     onAnimation
    0.88
    
    0.87
    tvguidetime
    0.82
     propOrder
    0.81
    GEBURTSDATUM
    0.79
     }{@
    0.76
    évaluateur
    0.76
     doubtnut
    0.76
     Мексичка
    0.75
    Activations Density 0.386%

    No Known Activations