© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15564
    Prev
    Next
    INDEX
    Explanations

    words that are important or essential to certain topics that are being discussed

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     neceffary
    -0.69
     دیکھیے
    -0.65
    MethodManager
    -0.65
     úteis
    -0.63
     adicionais
    -0.62
     necessárias
    -0.61
     насељу
    -0.59
     quæ
    -0.59
     itſelf
    -0.58
    neſs
    -0.57
    POSITIVE LOGITS
    SourceChecksum
    0.59
     Traveling
    0.58
    esine
    0.53
     Travelling
    0.53
     Référence
    0.53
     dAtA
    0.52
     millions
    0.52
     traveling
    0.52
    KURZBESCHREIBUNG
    0.50
    zko
    0.49
    Activations Density 16.444%

    No Known Activations