© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11571
    Prev
    Next
    INDEX
    Explanations

    sentences about people where they grew up or developed

    oai_token-act-pair · gemini-2.0-flash

    grow

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     growing
    -3.28
    growing
    -3.03
     grow
    -2.98
     Growing
    -2.98
    Growing
    -2.94
     grows
    -2.78
     GROW
    -2.70
     grew
    -2.58
    grow
    -2.56
     Grow
    -2.44
    POSITIVE LOGITS
    EndInit
    0.70
    UIControlState
    0.66
    发表于
    0.63
    DeleteBehavior
    0.62
    complexContent
    0.59
    PointerException
    0.54
    ResumeLayout
    0.53
     calendriers
    0.53
     AssemblyCompany
    0.50
     &___
    0.50
    Activations Density 3.220%

    No Known Activations