© 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. 15536
    Prev
    Next
    INDEX
    Explanations

    language related to research and technical documents involving data and increasing values

    oai_token-act-pair · gemini-2.0-flash

    the

    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
    Geplaatst
    -0.92
    ьаж
    -0.75
    
    -0.70
    testify
    -0.68
    EndInit
    -0.68
    PMailer
    -0.67
    LookAnd
    -0.65
    новништво
    -0.65
     initComponents
    -0.65
     незавершена
    -0.64
    POSITIVE LOGITS
    пит
    0.47
     stable
    0.46
     table
    0.45
    dsn
    0.45
    cipar
    0.44
     sanitaires
    0.44
    lük
    0.43
    Best
    0.41
    HashCode
    0.40
     خارجية
    0.40
    Activations Density 7.223%

    No Known Activations