© 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. 2098
    Prev
    Next
    INDEX
    Explanations

    descriptions of material and clothing

    oai_token-act-pair · 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
    endphp
    -0.60
     Printed
    -0.56
     Sturdy
    -0.53
     Inserts
    -0.52
     Panels
    -0.52
     Removable
    -0.52
    __":
    -0.51
    wicket
    -0.50
     Cushi
    -0.49
    __':
    -0.48
    POSITIVE LOGITS
    expandindo
    0.51
    Erfolge
    0.49
    lamó
    0.48
    PyExc
    0.48
     MessageBoxIcon
    0.46
    /*
    0.45
    raison
    0.45
    ̙
    0.45
     referenties
    0.45
    AccessorTable
    0.45
    Activations Density 9.783%

    No Known Activations