© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14480
    Prev
    Next
    INDEX
    Explanations

    positive adjectives such as "great", or words describing two things together

    oai_token-act-pair · gemini-2.0-flash

    great

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     which
    -0.79
     the
    -0.57
     he
    -0.54
     most
    -0.52
     my
    -0.52
     J
    -0.52
     Sud
    -0.51
     qu
    -0.50
     Ar
    -0.50
     where
    -0.50
    POSITIVE LOGITS
     Efq
    1.12
     Monfieur
    1.12
     pleaſure
    1.05
     auffi
    1.02
     Reſ
    1.02
     ainfi
    1.00
     Theſe
    0.99
     Eſ
    0.93
     uſed
    0.93
     Beſ
    0.92
    Activations Density 0.322%

    No Known Activations