© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13068
    Prev
    Next
    INDEX
    Explanations

    the word "first" alone or the beginning

    oai_token-act-pair · gemini-2.0-flash

    first

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     initially
    -0.88
    Initial
    -0.87
     inicialmente
    -0.87
     iniziale
    -0.87
     Initial
    -0.84
     initial
    -0.83
    initial
    -0.79
    AnimationsModule
    -0.79
     Initially
    -0.79
    Initially
    -0.79
    POSITIVE LOGITS
     kapcsolat
    0.47
    expandindo
    0.47
    Ход
    0.46
    CONCLUSION
    0.45
     emel
    0.45
    føring
    0.44
    NOWLEDG
    0.44
     ennek
    0.44
     umgangssprach
    0.44
     fær
    0.43
    Activations Density 20.858%

    No Known Activations